[{"id":"minimax-minimax-m3","slug":"minimax-minimax-m3","canonicalId":"minimax-minimax-m3","name":"MiniMax M3","provider":"MiniMax","family":null,"status":"active","variantType":"base","modelVersion":"minimax/minimax-m3-20260531","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"512000","apiAvailable":true,"pricing":{"prompt":3e-7,"completion":0.0000012},"inputPrice":0.3,"outputPrice":1.2,"cachedInputPrice":null,"price":"$0.30","overall":82,"fit":82,"overallScore":82,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":5,"overallScoreInputs":["coding","reasoning","computer_use","browsing","terminal"],"overallScoreMissing":["overall","agents"],"reasoning":93,"coding":80.5,"agents":29.5,"speed":null,"latency":null,"benchmarkScores":{"browsecomp":83.5,"gpqa-diamond":93,"osworld-verified":70.1,"swe-bench-verified":80.5,"terminal-bench-2-1":66,"coding":80.5,"reasoning":93,"computer_use":70.1,"browsing":83.5,"terminal":66},"benchmarkProvenance":{"browsecomp":{"url":"/benchmarks/browsecomp","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.864884+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/browsecomp"},"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.844305+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"},"osworld-verified":{"url":"/benchmarks/osworld","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.860106+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/osworld"},"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.348156+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.875137+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-10-14","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{"coding":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.348156+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.844305+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"computer_use":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.860106+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsing":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.864884+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.875137+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://platform.minimax.io/docs/guides/models","catalogSourceUrl":"https://minimax.io/","sourceUrl":"https://platform.minimax.io/docs/guides/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=minimax.io&sz=64","catalogRank":1,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"minimax-minimax-m3","name":"MiniMax M3","provider":"MiniMax","family":null,"status":"active","variantType":"base","modelVersion":"minimax/minimax-m3-20260531","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"512000","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.3,"outputPrice":1.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{"coding":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.348156+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.844305+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"computer_use":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.860106+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsing":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.864884+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.875137+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"browsecomp":83.5,"gpqa-diamond":93,"osworld-verified":70.1,"swe-bench-verified":80.5,"terminal-bench-2-1":66,"coding":80.5,"reasoning":93,"computer_use":70.1,"browsing":83.5,"terminal":66},"provenance":{"browsecomp":{"url":"/benchmarks/browsecomp","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.864884+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/browsecomp"},"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.844305+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"},"osworld-verified":{"url":"/benchmarks/osworld","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.860106+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/osworld"},"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.348156+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.875137+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"}},"composite":{"score":82,"version":"benchmark-composite-v1","coverage":5,"inputs":["coding","reasoning","computer_use","browsing","terminal"],"missing":["overall","agents"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"claude-mythos-5","slug":"claude-mythos-5","canonicalId":"claude-mythos-5","name":"Claude Mythos 5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text"],"context_length":null,"context":null,"contextWindow":null,"maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":null,"completion":null},"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"price":"N/A","overall":77.9,"fit":77.9,"overallScore":77.9,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":3,"overallScoreInputs":["overall","coding","terminal"],"overallScoreMissing":["reasoning","agents","computer_use","browsing"],"reasoning":null,"coding":95.5,"agents":null,"speed":null,"latency":null,"benchmarkScores":{"swe-bench-verified":95.5,"terminal-bench-2-1":88,"humanity-s-last-exam":64.5,"overall":64.5,"coding":95.5,"terminal":88},"benchmarkProvenance":{"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.796758+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.258908+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.857101+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-10-14","source":"Imported catalog record","sourceName":"Imported catalog record","sourceFetchedAt":null,"sourceSnapshotStatus":"not_synced","provenance":{"catalog":{"name":"Imported catalog record","url":null,"evidenceClass":"catalog fact","fetchedAt":null,"sourceUrl":null},"pricing":{"name":"Not reported","url":null,"evidenceClass":"catalog fact","observedAt":null,"sourceUrl":null},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.857101+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"coding":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.796758+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.258908+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":null,"catalogSourceUrl":null,"sourceUrl":null,"sourceUpdatedAt":{},"updated":"2026-08-25","releaseDate":null,"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":2,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"claude-mythos-5","name":"Claude Mythos 5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":null,"knowledgeCutoff":null,"license":null,"modalities":["Text"],"contextWindow":null,"maxOutputTokens":null,"apiAvailable":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Imported catalog record","url":null,"evidenceClass":"catalog fact","fetchedAt":null,"sourceUrl":null},"pricing":{"name":"Not reported","url":null,"evidenceClass":"catalog fact","observedAt":null,"sourceUrl":null},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.857101+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"coding":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.796758+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.258908+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"swe-bench-verified":95.5,"terminal-bench-2-1":88,"humanity-s-last-exam":64.5,"overall":64.5,"coding":95.5,"terminal":88},"provenance":{"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.796758+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.258908+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.857101+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":{"score":77.9,"version":"benchmark-composite-v1","coverage":3,"inputs":["overall","coding","terminal"],"missing":["reasoning","agents","computer_use","browsing"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"moonshotai-kimi-k3","slug":"moonshotai-kimi-k3","canonicalId":"moonshotai-kimi-k3","name":"Kimi K3","provider":"Moonshot AI","family":null,"status":"active","variantType":"base","modelVersion":"moonshotai/kimi-k3-20260715","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":7e-7,"completion":0.0000135},"inputPrice":0.7,"outputPrice":13.5,"cachedInputPrice":null,"price":"$0.70","overall":74.1,"fit":74.1,"overallScore":74.1,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":4,"overallScoreInputs":["overall","reasoning","browsing","terminal"],"overallScoreMissing":["coding","agents","computer_use"],"reasoning":93.5,"coding":76.2,"agents":50,"speed":null,"latency":null,"benchmarkScores":{"browsecomp":91.2,"terminal-bench-2-1":88.3,"humanity-s-last-exam":56,"overall":56,"browsing":91.2,"terminal":88.3,"gpqa-diamond":93.5,"reasoning":93.5},"benchmarkProvenance":{"browsecomp":{"url":"/benchmarks/browsecomp","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.862327+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/browsecomp"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.870631+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.811129+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.841683+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-10-14","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.811129+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.841683+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsing":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.862327+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.870631+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://platform.moonshot.ai/docs/guide/models","catalogSourceUrl":"https://moonshot.ai/","sourceUrl":"https://platform.moonshot.ai/docs/guide/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=moonshot.ai&sz=64","catalogRank":3,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"moonshotai-kimi-k3","name":"Kimi K3","provider":"Moonshot AI","family":null,"status":"active","variantType":"base","modelVersion":"moonshotai/kimi-k3-20260715","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.7,"outputPrice":13.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.811129+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.841683+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsing":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.862327+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.870631+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"browsecomp":91.2,"terminal-bench-2-1":88.3,"humanity-s-last-exam":56,"overall":56,"browsing":91.2,"terminal":88.3,"gpqa-diamond":93.5,"reasoning":93.5},"provenance":{"browsecomp":{"url":"/benchmarks/browsecomp","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.862327+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/browsecomp"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.870631+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.811129+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.841683+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"}},"composite":{"score":74.1,"version":"benchmark-composite-v1","coverage":4,"inputs":["overall","reasoning","browsing","terminal"],"missing":["coding","agents","computer_use"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"claude-sonnet-5","slug":"claude-sonnet-5","canonicalId":"claude-sonnet-5","name":"Claude Sonnet 5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-sonnet-5-20260630","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.00001},"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"price":"$2.00","overall":72.9,"fit":72.9,"overallScore":72.9,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":2,"overallScoreInputs":["overall","reasoning"],"overallScoreMissing":["coding","agents","computer_use","browsing","terminal"],"reasoning":96.2,"coding":71.5,"agents":43.6,"speed":null,"latency":null,"benchmarkScores":{"gpqa-diamond":96.2,"osworld-verified":81.2,"humanity-s-last-exam":57.4,"overall":57.4,"reasoning":96.2,"computer_use":81.2},"benchmarkProvenance":{"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.822905+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"},"osworld-verified":{"url":"/benchmarks/osworld","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.147337+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/osworld"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.645611+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-08-25","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.645611+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.822905+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":4,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"claude-sonnet-5","name":"Claude Sonnet 5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-sonnet-5-20260630","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.645611+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.822905+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"gpqa-diamond":96.2,"osworld-verified":81.2,"humanity-s-last-exam":57.4,"overall":57.4,"reasoning":96.2,"computer_use":81.2},"provenance":{"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.822905+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"},"osworld-verified":{"url":"/benchmarks/osworld","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.147337+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/osworld"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.645611+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":{"score":72.9,"version":"benchmark-composite-v1","coverage":2,"inputs":["overall","reasoning"],"missing":["coding","agents","computer_use","browsing","terminal"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"moonshotai-kimi-k2-6","slug":"moonshotai-kimi-k2-6","canonicalId":"moonshotai-kimi-k2-6","name":"Kimi K2.6","provider":"Moonshot AI","family":null,"status":"active","variantType":"base","modelVersion":"moonshotai/kimi-k2.6-20260420","modalities":["Text","Image","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":6.5e-7,"completion":0.00000341},"inputPrice":0.65,"outputPrice":3.41,"cachedInputPrice":null,"price":"$0.65","overall":72.7,"fit":72.7,"overallScore":72.7,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":5,"overallScoreInputs":["overall","coding","reasoning","computer_use","browsing"],"overallScoreMissing":["agents","terminal"],"reasoning":90.5,"coding":80.2,"agents":20.5,"speed":342.6,"latency":null,"benchmarkScores":{"humanity-s-last-exam":54,"overall":54,"browsecomp":83.2,"gpqa-diamond":90.5,"osworld-verified":73.1,"swe-bench-verified":80.2,"coding":80.2,"reasoning":90.5,"computer_use":73.1,"browsing":83.2},"benchmarkProvenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.818479+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsecomp":{"url":"/benchmarks/browsecomp","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.867472+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/browsecomp"},"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.849004+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"},"osworld-verified":{"url":"/benchmarks/osworld","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.858948+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/osworld"},"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.350022+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-10-14","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.818479+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"coding":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.350022+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.849004+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"computer_use":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.858948+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsing":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.867472+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://platform.moonshot.ai/docs/guide/models","catalogSourceUrl":"https://moonshot.ai/","sourceUrl":"https://platform.moonshot.ai/docs/guide/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=moonshot.ai&sz=64","catalogRank":5,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"moonshotai-kimi-k2-6","name":"Kimi K2.6","provider":"Moonshot AI","family":null,"status":"active","variantType":"base","modelVersion":"moonshotai/kimi-k2.6-20260420","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.65,"outputPrice":3.41,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.818479+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"coding":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.350022+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.849004+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"computer_use":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.858948+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsing":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.867472+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"humanity-s-last-exam":54,"overall":54,"browsecomp":83.2,"gpqa-diamond":90.5,"osworld-verified":73.1,"swe-bench-verified":80.2,"coding":80.2,"reasoning":90.5,"computer_use":73.1,"browsing":83.2},"provenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.818479+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsecomp":{"url":"/benchmarks/browsecomp","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.867472+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/browsecomp"},"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.849004+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"},"osworld-verified":{"url":"/benchmarks/osworld","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.858948+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/osworld"},"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.350022+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"}},"composite":{"score":72.7,"version":"benchmark-composite-v1","coverage":5,"inputs":["overall","coding","reasoning","computer_use","browsing"],"missing":["agents","terminal"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-v4-pro","slug":"deepseek-v4-pro","canonicalId":"deepseek-v4-pro","name":"DeepSeek V4 Pro","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text"],"context_length":null,"context":null,"contextWindow":null,"maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":null,"completion":null},"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"price":"N/A","overall":70.4,"fit":70.4,"overallScore":70.4,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":4,"overallScoreInputs":["overall","coding","reasoning","browsing"],"overallScoreMissing":["agents","computer_use","terminal"],"reasoning":90.1,"coding":80.6,"agents":null,"speed":null,"latency":null,"benchmarkScores":{"browsecomp":83.4,"gpqa-diamond":90.1,"swe-bench-verified":80.6,"humanity-s-last-exam":48.2,"overall":48.2,"coding":80.6,"reasoning":90.1,"browsing":83.4},"benchmarkProvenance":{"browsecomp":{"url":"/benchmarks/browsecomp","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.866251+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/browsecomp"},"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.85132+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"},"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.346039+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.823633+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-10-14","source":"Imported catalog record","sourceName":"Imported catalog record","sourceFetchedAt":null,"sourceSnapshotStatus":"not_synced","provenance":{"catalog":{"name":"Imported catalog record","url":null,"evidenceClass":"catalog fact","fetchedAt":null,"sourceUrl":null},"pricing":{"name":"Not reported","url":null,"evidenceClass":"catalog fact","observedAt":null,"sourceUrl":null},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.823633+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"coding":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.346039+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.85132+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsing":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.866251+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":null,"catalogSourceUrl":null,"sourceUrl":null,"sourceUpdatedAt":{},"updated":"2026-08-25","releaseDate":null,"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":6,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-v4-pro","name":"DeepSeek V4 Pro","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":null,"knowledgeCutoff":null,"license":null,"modalities":["Text"],"contextWindow":null,"maxOutputTokens":null,"apiAvailable":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Imported catalog record","url":null,"evidenceClass":"catalog fact","fetchedAt":null,"sourceUrl":null},"pricing":{"name":"Not reported","url":null,"evidenceClass":"catalog fact","observedAt":null,"sourceUrl":null},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.823633+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"coding":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.346039+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.85132+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsing":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.866251+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"browsecomp":83.4,"gpqa-diamond":90.1,"swe-bench-verified":80.6,"humanity-s-last-exam":48.2,"overall":48.2,"coding":80.6,"reasoning":90.1,"browsing":83.4},"provenance":{"browsecomp":{"url":"/benchmarks/browsecomp","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.866251+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/browsecomp"},"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.85132+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"},"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.346039+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.823633+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":{"score":70.4,"version":"benchmark-composite-v1","coverage":4,"inputs":["overall","coding","reasoning","browsing"],"missing":["agents","computer_use","terminal"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-5-2","slug":"z-ai-glm-5-2","canonicalId":"z-ai-glm-5-2","name":"GLM 5.2","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-5.2-20260616","modalities":["Text","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":6e-8,"completion":0.000007},"inputPrice":0.06,"outputPrice":7,"cachedInputPrice":null,"price":"$0.06","overall":70.4,"fit":70.4,"overallScore":70.4,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":3,"overallScoreInputs":["overall","reasoning","terminal"],"overallScoreMissing":["coding","agents","computer_use","browsing"],"reasoning":91.2,"coding":68.8,"agents":38.4,"speed":347,"latency":null,"benchmarkScores":{"humanity-s-last-exam":54.7,"overall":54.7,"gpqa-diamond":91.2,"terminal-bench-2-1":81,"reasoning":91.2,"terminal":81},"benchmarkProvenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.815785+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.846683+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.873726+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-10-14","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.815785+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.846683+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.873726+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":7,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-5-2","name":"GLM 5.2","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-5.2-20260616","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.06,"outputPrice":7,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.815785+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.846683+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.873726+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"humanity-s-last-exam":54.7,"overall":54.7,"gpqa-diamond":91.2,"terminal-bench-2-1":81,"reasoning":91.2,"terminal":81},"provenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.815785+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.846683+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.873726+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"}},"composite":{"score":70.4,"version":"benchmark-composite-v1","coverage":3,"inputs":["overall","reasoning","terminal"],"missing":["coding","agents","computer_use","browsing"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-6-sol","slug":"openai-gpt-5-6-sol","canonicalId":"openai-gpt-5-6-sol","name":"GPT-5.6 Sol","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.6-sol-20260709","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.00001},"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"price":"$2.00","overall":70.2,"fit":70.2,"overallScore":70.2,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":6,"overallScoreInputs":["overall","coding","reasoning","agents","browsing","terminal"],"overallScoreMissing":["computer_use"],"reasoning":94.6,"coding":96.2,"agents":18.1,"speed":null,"latency":null,"benchmarkScores":{"autobench":18.1,"browsecomp":92.2,"gpqa-diamond":94.6,"terminal-bench-2-1":88.8,"humanity-s-last-exam":47.2,"overall":47.2,"reasoning":94.6,"agents":18.1,"automation":18.1,"browsing":92.2,"terminal":88.8,"swe-bench-verified":96.2,"coding":96.2},"benchmarkProvenance":{"autobench":{"url":"/benchmarks/autobench","name":"Benchmark registry","observedAt":"2026-08-27T14:10:35.698036+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/autobench"},"browsecomp":{"url":"/benchmarks/browsecomp","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.178574+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/browsecomp"},"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.999534+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.248319+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.932789+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.78887+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-10-14","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.932789+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"coding":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.78887+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.999534+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"agents":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-27T14:10:35.698036+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"automation":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-27T14:10:35.698036+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsing":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.178574+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.248319+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-sol","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-sol","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":8,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-6-sol","name":"GPT-5.6 Sol","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.6-sol-20260709","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.932789+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"coding":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.78887+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.999534+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"agents":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-27T14:10:35.698036+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"automation":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-27T14:10:35.698036+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsing":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.178574+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.248319+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"autobench":18.1,"browsecomp":92.2,"gpqa-diamond":94.6,"terminal-bench-2-1":88.8,"humanity-s-last-exam":47.2,"overall":47.2,"reasoning":94.6,"agents":18.1,"automation":18.1,"browsing":92.2,"terminal":88.8,"swe-bench-verified":96.2,"coding":96.2},"provenance":{"autobench":{"url":"/benchmarks/autobench","name":"Benchmark registry","observedAt":"2026-08-27T14:10:35.698036+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/autobench"},"browsecomp":{"url":"/benchmarks/browsecomp","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.178574+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/browsecomp"},"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.999534+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.248319+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.932789+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.78887+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"}},"composite":{"score":70.2,"version":"benchmark-composite-v1","coverage":6,"inputs":["overall","coding","reasoning","agents","browsing","terminal"],"missing":["computer_use"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-6-astra","slug":"openai-gpt-6-astra","canonicalId":"openai-gpt-6-astra","name":"GPT-6 Astra","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-6-astra-20260903","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00001,"completion":0.00005},"inputPrice":10,"outputPrice":50,"cachedInputPrice":null,"price":"$10.00","overall":69.3,"fit":69.3,"overallScore":69.3,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":4,"overallScoreInputs":["overall","reasoning","agents","browsing"],"overallScoreMissing":["coding","computer_use","terminal"],"reasoning":96,"coding":76.9,"agents":41.4,"speed":null,"latency":null,"benchmarkScores":{"autobench":41.4,"browsecomp":91.5,"gpqa-diamond":96,"humanity-s-last-exam":57.2,"overall":57.2,"reasoning":96,"agents":41.4,"automation":41.4,"browsing":91.5},"benchmarkProvenance":{"autobench":{"url":"/benchmarks/autobench","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.102227+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/autobench"},"browsecomp":{"url":"/benchmarks/browsecomp","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.183793+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/browsecomp"},"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.98517+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.884223+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-09-15","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.884223+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.98517+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"agents":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.102227+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"automation":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.102227+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsing":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.183793+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-6-astra","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-6-astra","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":9,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-6-astra","name":"GPT-6 Astra","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-6-astra-20260903","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":10,"outputPrice":50,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.884223+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.98517+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"agents":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.102227+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"automation":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.102227+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsing":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.183793+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"autobench":41.4,"browsecomp":91.5,"gpqa-diamond":96,"humanity-s-last-exam":57.2,"overall":57.2,"reasoning":96,"agents":41.4,"automation":41.4,"browsing":91.5},"provenance":{"autobench":{"url":"/benchmarks/autobench","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.102227+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/autobench"},"browsecomp":{"url":"/benchmarks/browsecomp","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.183793+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/browsecomp"},"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.98517+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.884223+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":{"score":69.3,"version":"benchmark-composite-v1","coverage":4,"inputs":["overall","reasoning","agents","browsing"],"missing":["coding","computer_use","terminal"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-v4-flash","slug":"deepseek-v4-flash","canonicalId":"deepseek-v4-flash","name":"DeepSeek V4 Flash","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text"],"context_length":null,"context":null,"contextWindow":null,"maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":null,"completion":null},"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"price":"N/A","overall":64.7,"fit":64.7,"overallScore":64.7,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":3,"overallScoreInputs":["overall","coding","browsing"],"overallScoreMissing":["reasoning","agents","computer_use","terminal"],"reasoning":null,"coding":79,"agents":null,"speed":null,"latency":null,"benchmarkScores":{"browsecomp":85.9,"swe-bench-verified":79,"humanity-s-last-exam":51.6,"overall":51.6,"coding":79,"browsing":85.9},"benchmarkProvenance":{"browsecomp":{"url":"/benchmarks/browsecomp","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.863663+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/browsecomp"},"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.351846+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.821345+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-10-14","source":"Imported catalog record","sourceName":"Imported catalog record","sourceFetchedAt":null,"sourceSnapshotStatus":"not_synced","provenance":{"catalog":{"name":"Imported catalog record","url":null,"evidenceClass":"catalog fact","fetchedAt":null,"sourceUrl":null},"pricing":{"name":"Not reported","url":null,"evidenceClass":"catalog fact","observedAt":null,"sourceUrl":null},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.821345+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"coding":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.351846+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsing":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.863663+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":null,"catalogSourceUrl":null,"sourceUrl":null,"sourceUpdatedAt":{},"updated":"2026-08-25","releaseDate":null,"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":10,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-v4-flash","name":"DeepSeek V4 Flash","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":null,"knowledgeCutoff":null,"license":null,"modalities":["Text"],"contextWindow":null,"maxOutputTokens":null,"apiAvailable":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Imported catalog record","url":null,"evidenceClass":"catalog fact","fetchedAt":null,"sourceUrl":null},"pricing":{"name":"Not reported","url":null,"evidenceClass":"catalog fact","observedAt":null,"sourceUrl":null},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.821345+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"coding":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.351846+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsing":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.863663+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"browsecomp":85.9,"swe-bench-verified":79,"humanity-s-last-exam":51.6,"overall":51.6,"coding":79,"browsing":85.9},"provenance":{"browsecomp":{"url":"/benchmarks/browsecomp","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.863663+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/browsecomp"},"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.351846+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.821345+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":{"score":64.7,"version":"benchmark-composite-v1","coverage":3,"inputs":["overall","coding","browsing"],"missing":["reasoning","agents","computer_use","terminal"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"gemini-3-1-pro","slug":"gemini-3-1-pro","canonicalId":"gemini-3-1-pro","name":"Gemini 3.1 Pro","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text"],"context_length":null,"context":null,"contextWindow":null,"maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":null,"completion":null},"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"price":"N/A","overall":64.4,"fit":64.4,"overallScore":64.4,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":2,"overallScoreInputs":["overall","reasoning"],"overallScoreMissing":["coding","agents","computer_use","browsing","terminal"],"reasoning":94.3,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{"gpqa-diamond":94.3,"humanity-s-last-exam":44.4,"overall":44.4,"reasoning":94.3},"benchmarkProvenance":{"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.017188+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.957003+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-09-15","source":"Imported catalog record","sourceName":"Imported catalog record","sourceFetchedAt":null,"sourceSnapshotStatus":"not_synced","provenance":{"catalog":{"name":"Imported catalog record","url":null,"evidenceClass":"catalog fact","fetchedAt":null,"sourceUrl":null},"pricing":{"name":"Not reported","url":null,"evidenceClass":"catalog fact","observedAt":null,"sourceUrl":null},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.957003+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.017188+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":null,"catalogSourceUrl":null,"sourceUrl":null,"sourceUpdatedAt":{},"updated":"2026-08-25","releaseDate":null,"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":11,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"gemini-3-1-pro","name":"Gemini 3.1 Pro","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":null,"knowledgeCutoff":null,"license":null,"modalities":["Text"],"contextWindow":null,"maxOutputTokens":null,"apiAvailable":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Imported catalog record","url":null,"evidenceClass":"catalog fact","fetchedAt":null,"sourceUrl":null},"pricing":{"name":"Not reported","url":null,"evidenceClass":"catalog fact","observedAt":null,"sourceUrl":null},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.957003+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.017188+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"gpqa-diamond":94.3,"humanity-s-last-exam":44.4,"overall":44.4,"reasoning":94.3},"provenance":{"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.017188+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.957003+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":{"score":64.4,"version":"benchmark-composite-v1","coverage":2,"inputs":["overall","reasoning"],"missing":["coding","agents","computer_use","browsing","terminal"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"claude-opus-5","slug":"claude-opus-5","canonicalId":"claude-opus-5","name":"Claude Opus 5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-opus-5-20260723","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000005,"completion":0.000025},"inputPrice":5,"outputPrice":25,"cachedInputPrice":null,"price":"$5.00","overall":59,"fit":59,"overallScore":59,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":3,"overallScoreInputs":["overall","agents","browsing"],"overallScoreMissing":["coding","reasoning","computer_use","terminal"],"reasoning":50.8,"coding":78,"agents":26,"speed":null,"latency":null,"benchmarkScores":{"autobench":26,"browsecomp":90.8,"humanity-s-last-exam":64.7,"overall":64.7,"agents":26,"automation":26,"browsing":90.8},"benchmarkProvenance":{"autobench":{"url":"/benchmarks/autobench","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.955439+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/autobench"},"browsecomp":{"url":"/benchmarks/browsecomp","name":"Benchmark registry","observedAt":"2026-08-25T09:15:25.056326+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/browsecomp"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.614394+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-08-25","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.614394+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"agents":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.955439+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"automation":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.955439+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsing":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:25.056326+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":12,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"claude-opus-5","name":"Claude Opus 5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-opus-5-20260723","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":5,"outputPrice":25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.614394+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"agents":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.955439+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"automation":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.955439+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsing":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:25.056326+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"autobench":26,"browsecomp":90.8,"humanity-s-last-exam":64.7,"overall":64.7,"agents":26,"automation":26,"browsing":90.8},"provenance":{"autobench":{"url":"/benchmarks/autobench","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.955439+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/autobench"},"browsecomp":{"url":"/benchmarks/browsecomp","name":"Benchmark registry","observedAt":"2026-08-25T09:15:25.056326+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/browsecomp"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.614394+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":{"score":59,"version":"benchmark-composite-v1","coverage":3,"inputs":["overall","agents","browsing"],"missing":["coding","reasoning","computer_use","terminal"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-5-3-flash","slug":"z-ai-glm-5-3-flash","canonicalId":"z-ai-glm-5-3-flash","name":"GLM 5.3 Flash","provider":"Z.ai","family":null,"status":"active","variantType":"fast","modelVersion":"z-ai/glm-5.3-flash-20260826","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":3.6e-8,"completion":9e-7},"inputPrice":0.036,"outputPrice":0.8999999999999999,"cachedInputPrice":null,"price":"$0.04","overall":57.1,"fit":57.1,"overallScore":57.1,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":3,"overallScoreInputs":["overall","agents","terminal"],"overallScoreMissing":["coding","reasoning","computer_use","browsing"],"reasoning":41.8,"coding":71.5,"agents":48.8,"speed":null,"latency":null,"benchmarkScores":{"autobench":48.8,"terminal-bench-2-1":84.3,"humanity-s-last-exam":55.3,"overall":55.3,"agents":48.8,"automation":48.8,"terminal":84.3},"benchmarkProvenance":{"autobench":{"url":"/benchmarks/autobench","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.854839+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/autobench"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.872443+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.813346+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-10-14","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.813346+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"agents":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.854839+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"automation":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.854839+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.872443+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":13,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-5-3-flash","name":"GLM 5.3 Flash","provider":"Z.ai","family":null,"status":"active","variantType":"fast","modelVersion":"z-ai/glm-5.3-flash-20260826","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.036,"outputPrice":0.8999999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.813346+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"agents":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.854839+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"automation":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.854839+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.872443+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"autobench":48.8,"terminal-bench-2-1":84.3,"humanity-s-last-exam":55.3,"overall":55.3,"agents":48.8,"automation":48.8,"terminal":84.3},"provenance":{"autobench":{"url":"/benchmarks/autobench","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.854839+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/autobench"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.872443+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.813346+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":{"score":57.1,"version":"benchmark-composite-v1","coverage":3,"inputs":["overall","agents","terminal"],"missing":["coding","reasoning","computer_use","browsing"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-fable-5-1","slug":"anthropic-claude-fable-5-1","canonicalId":"anthropic-claude-fable-5-1","name":"Claude Fable 5.1","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-fable-5.1-20260831","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00001,"completion":0.00005},"inputPrice":10,"outputPrice":50,"cachedInputPrice":null,"price":"$10.00","overall":56.6,"fit":56.6,"overallScore":56.6,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":2,"overallScoreInputs":["overall","agents"],"overallScoreMissing":["coding","reasoning","computer_use","browsing","terminal"],"reasoning":53.4,"coding":81.6,"agents":31.4,"speed":null,"latency":null,"benchmarkScores":{"autobench":31.4,"humanity-s-last-exam":65,"overall":65,"agents":31.4,"automation":31.4},"benchmarkProvenance":{"autobench":{"url":"/benchmarks/autobench","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.113511+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/autobench"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.800408+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-09-15","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.800408+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"agents":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.113511+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"automation":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.113511+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":14,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-fable-5-1","name":"Claude Fable 5.1","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-fable-5.1-20260831","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":10,"outputPrice":50,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.800408+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"agents":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.113511+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"automation":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.113511+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"autobench":31.4,"humanity-s-last-exam":65,"overall":65,"agents":31.4,"automation":31.4},"provenance":{"autobench":{"url":"/benchmarks/autobench","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.113511+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/autobench"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.800408+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":{"score":56.6,"version":"benchmark-composite-v1","coverage":2,"inputs":["overall","agents"],"missing":["coding","reasoning","computer_use","browsing","terminal"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"claude-fable-5","slug":"claude-fable-5","canonicalId":"claude-fable-5","name":"Claude Fable 5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-5-fable-20260609","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00001,"completion":0.00005},"inputPrice":10,"outputPrice":50,"cachedInputPrice":null,"price":"$10.00","overall":51.8,"fit":51.8,"overallScore":51.8,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":3,"overallScoreInputs":["agents","browsing","terminal"],"overallScoreMissing":["overall","coding","reasoning","computer_use"],"reasoning":49.6,"coding":76.5,"agents":17.4,"speed":null,"latency":null,"benchmarkScores":{"autobench":17.4,"browsecomp":88,"osworld-verified":85,"swe-bench-verified":95,"terminal-bench-2-1":84.3,"coding":95,"agents":17.4,"automation":17.4,"computer_use":85,"browsing":88,"terminal":84.3},"benchmarkProvenance":{"autobench":{"url":"/benchmarks/autobench","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.982963+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/autobench"},"browsecomp":{"url":"/benchmarks/browsecomp","name":"Benchmark registry","observedAt":"2026-08-25T09:15:25.060803+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/browsecomp"},"osworld-verified":{"url":"/benchmarks/osworld","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.137742+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/osworld"},"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.800223+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-08-25T09:15:25.11424+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-08-25","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{"agents":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.982963+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"automation":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.982963+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsing":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:25.060803+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:25.11424+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":15,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"claude-fable-5","name":"Claude Fable 5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-5-fable-20260609","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":10,"outputPrice":50,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{"agents":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.982963+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"automation":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.982963+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"browsing":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:25.060803+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:25.11424+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"autobench":17.4,"browsecomp":88,"osworld-verified":85,"swe-bench-verified":95,"terminal-bench-2-1":84.3,"coding":95,"agents":17.4,"automation":17.4,"computer_use":85,"browsing":88,"terminal":84.3},"provenance":{"autobench":{"url":"/benchmarks/autobench","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.982963+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/autobench"},"browsecomp":{"url":"/benchmarks/browsecomp","name":"Benchmark registry","observedAt":"2026-08-25T09:15:25.060803+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/browsecomp"},"osworld-verified":{"url":"/benchmarks/osworld","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.137742+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/osworld"},"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.800223+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-08-25T09:15:25.11424+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"}},"composite":{"score":51.8,"version":"benchmark-composite-v1","coverage":3,"inputs":["agents","browsing","terminal"],"missing":["overall","coding","reasoning","computer_use"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-5","slug":"openai-gpt-5-5","canonicalId":"openai-gpt-5-5","name":"GPT-5.5","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.5-20260423","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000005,"completion":0.00003},"inputPrice":5,"outputPrice":30,"cachedInputPrice":null,"price":"$5.00","overall":50.7,"fit":50.7,"overallScore":50.7,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":2,"overallScoreInputs":["overall","computer_use"],"overallScoreMissing":["coding","reasoning","agents","browsing","terminal"],"reasoning":38.4,"coding":74.9,"agents":36.4,"speed":null,"latency":null,"benchmarkScores":{"humanity-s-last-exam":41.4,"overall":41.4,"osworld-verified":78.7,"computer_use":78.7},"benchmarkProvenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.96708+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"osworld-verified":{"url":"/benchmarks/osworld","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.155227+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/osworld"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-09-15","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.96708+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"computer_use":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.155227+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.5","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.5","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":16,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-5","name":"GPT-5.5","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.5-20260423","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":5,"outputPrice":30,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.96708+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"computer_use":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.155227+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"humanity-s-last-exam":41.4,"overall":41.4,"osworld-verified":78.7,"computer_use":78.7},"provenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.96708+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"osworld-verified":{"url":"/benchmarks/osworld","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.155227+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/osworld"}},"composite":{"score":50.7,"version":"benchmark-composite-v1","coverage":2,"inputs":["overall","computer_use"],"missing":["coding","reasoning","agents","browsing","terminal"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"moonshotai-kimi-k2-5","slug":"moonshotai-kimi-k2-5","canonicalId":"moonshotai-kimi-k2-5","name":"Kimi K2.5","provider":"Moonshot AI","family":null,"status":"active","variantType":"base","modelVersion":"moonshotai/kimi-k2.5-0127","modalities":["Text","Image","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":5e-7,"completion":0.0000025},"inputPrice":0.5,"outputPrice":2.5,"cachedInputPrice":null,"price":"$0.50","overall":49,"fit":49,"overallScore":49,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":3,"overallScoreInputs":["overall","coding","terminal"],"overallScoreMissing":["reasoning","agents","computer_use","browsing"],"reasoning":23.5,"coding":76.8,"agents":0,"speed":337.7,"latency":null,"benchmarkScores":{"humanity-s-last-exam":30.1,"overall":30.1,"swe-bench-verified":76.8,"terminal-bench-2-1":50.8,"coding":76.8,"terminal":50.8},"benchmarkProvenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.829217+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.353665+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.876897+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-10-14","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.829217+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"coding":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.353665+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.876897+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://platform.moonshot.ai/docs/guide/models","catalogSourceUrl":"https://moonshot.ai/","sourceUrl":"https://platform.moonshot.ai/docs/guide/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=moonshot.ai&sz=64","catalogRank":17,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"moonshotai-kimi-k2-5","name":"Kimi K2.5","provider":"Moonshot AI","family":null,"status":"active","variantType":"base","modelVersion":"moonshotai/kimi-k2.5-0127","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.5,"outputPrice":2.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.829217+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"coding":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.353665+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.876897+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"humanity-s-last-exam":30.1,"overall":30.1,"swe-bench-verified":76.8,"terminal-bench-2-1":50.8,"coding":76.8,"terminal":50.8},"provenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.829217+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-09-26T13:56:12.353665+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.876897+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"}},"composite":{"score":49,"version":"benchmark-composite-v1","coverage":3,"inputs":["overall","coding","terminal"],"missing":["reasoning","agents","computer_use","browsing"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-7-flash","slug":"google-gemini-3-7-flash","canonicalId":"google-gemini-3-7-flash","name":"Gemini 3.7 Flash","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-3.7-flash-20260813","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":7.5e-7,"completion":0.00000375},"inputPrice":0.75,"outputPrice":3.75,"cachedInputPrice":null,"price":"$0.75","overall":48.9,"fit":48.9,"overallScore":48.9,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":2,"overallScoreInputs":["agents","terminal"],"overallScoreMissing":["overall","coding","reasoning","computer_use","browsing"],"reasoning":39.6,"coding":71.5,"agents":30.4,"speed":null,"latency":null,"benchmarkScores":{"autobench":30.4,"terminal-bench-2-1":85.8,"agents":30.4,"automation":30.4,"terminal":85.8},"benchmarkProvenance":{"autobench":{"url":"/benchmarks/autobench","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.125948+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/autobench"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.263661+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-09-15","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{"agents":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.125948+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"automation":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.125948+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.263661+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":18,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-7-flash","name":"Gemini 3.7 Flash","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-3.7-flash-20260813","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.75,"outputPrice":3.75,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{"agents":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.125948+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"automation":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.125948+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.263661+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"autobench":30.4,"terminal-bench-2-1":85.8,"agents":30.4,"automation":30.4,"terminal":85.8},"provenance":{"autobench":{"url":"/benchmarks/autobench","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.125948+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/autobench"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.263661+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"}},"composite":{"score":48.9,"version":"benchmark-composite-v1","coverage":2,"inputs":["agents","terminal"],"missing":["overall","coding","reasoning","computer_use","browsing"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"claude-opus-4-8","slug":"claude-opus-4-8","canonicalId":"claude-opus-4-8","name":"Claude Opus 4.8","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4.8-opus-20260528","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000005,"completion":0.000025},"inputPrice":5,"outputPrice":25,"cachedInputPrice":null,"price":"$5.00","overall":47.3,"fit":47.3,"overallScore":47.3,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":2,"overallScoreInputs":["overall","agents"],"overallScoreMissing":["coding","reasoning","computer_use","browsing","terminal"],"reasoning":41.8,"coding":74.3,"agents":15.5,"speed":null,"latency":null,"benchmarkScores":{"autobench":15.5,"osworld-verified":83.4,"swe-bench-verified":88.6,"humanity-s-last-exam":57.9,"overall":57.9,"coding":88.6,"agents":15.5,"automation":15.5,"computer_use":83.4},"benchmarkProvenance":{"autobench":{"url":"/benchmarks/autobench","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.992211+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/autobench"},"osworld-verified":{"url":"/benchmarks/osworld","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.142179+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/osworld"},"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.807294+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.63046+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-08-25","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.63046+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"agents":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.992211+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"automation":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.992211+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":19,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"claude-opus-4-8","name":"Claude Opus 4.8","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4.8-opus-20260528","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":5,"outputPrice":25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.63046+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"agents":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.992211+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"automation":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.992211+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"autobench":15.5,"osworld-verified":83.4,"swe-bench-verified":88.6,"humanity-s-last-exam":57.9,"overall":57.9,"coding":88.6,"agents":15.5,"automation":15.5,"computer_use":83.4},"provenance":{"autobench":{"url":"/benchmarks/autobench","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.992211+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/autobench"},"osworld-verified":{"url":"/benchmarks/osworld","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.142179+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/osworld"},"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.807294+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"},"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.63046+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":{"score":47.3,"version":"benchmark-composite-v1","coverage":2,"inputs":["overall","agents"],"missing":["coding","reasoning","computer_use","browsing","terminal"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"moonshotai-kimi-k2-thinking","slug":"moonshotai-kimi-k2-thinking","canonicalId":"moonshotai-kimi-k2-thinking","name":"Kimi K2 Thinking","provider":"Moonshot AI","family":null,"status":"active","variantType":"base","modelVersion":"moonshotai/kimi-k2-thinking-20251106","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"98304","apiAvailable":true,"pricing":{"prompt":6e-7,"completion":0.0000025},"inputPrice":0.6,"outputPrice":2.5,"cachedInputPrice":null,"price":"$0.60","overall":43.6,"fit":43.6,"overallScore":43.6,"overallScoreVersion":"benchmark-composite-v1","overallScoreCoverage":2,"overallScoreInputs":["overall","terminal"],"overallScoreMissing":["coding","reasoning","agents","computer_use","browsing"],"reasoning":22,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{"humanity-s-last-exam":44.9,"overall":44.9,"terminal-bench-2-1":35.7,"terminal":35.7},"benchmarkProvenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.826207+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-08-27T14:10:35.661204+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-10-14","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.826207+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-27T14:10:35.661204+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://platform.moonshot.ai/docs/guide/models","catalogSourceUrl":"https://moonshot.ai/","sourceUrl":"https://platform.moonshot.ai/docs/guide/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=moonshot.ai&sz=64","catalogRank":20,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"moonshotai-kimi-k2-thinking","name":"Kimi K2 Thinking","provider":"Moonshot AI","family":null,"status":"active","variantType":"base","modelVersion":"moonshotai/kimi-k2-thinking-20251106","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"98304","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.6,"outputPrice":2.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.826207+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-27T14:10:35.661204+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"humanity-s-last-exam":44.9,"overall":44.9,"terminal-bench-2-1":35.7,"terminal":35.7},"provenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.826207+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"},"terminal-bench-2-1":{"url":"/benchmarks/terminal-bench-2-1","name":"Benchmark registry","observedAt":"2026-08-27T14:10:35.661204+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/terminal-bench-2-1"}},"composite":{"score":43.6,"version":"benchmark-composite-v1","coverage":2,"inputs":["overall","terminal"],"missing":["coding","reasoning","agents","computer_use","browsing"]}},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"claude-3-opus","slug":"claude-3-opus","canonicalId":"claude-3-opus","name":"Claude 3 Opus","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text"],"context_length":null,"context":null,"contextWindow":null,"maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":null,"completion":null},"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"price":"N/A","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":1,"overallScoreInputs":["reasoning"],"overallScoreMissing":["overall","coding","agents","computer_use","browsing","terminal"],"reasoning":95.4,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{"gpqa-diamond":95.4,"reasoning":95.4},"benchmarkProvenance":{"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.992023+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-09-15","source":"Imported catalog record","sourceName":"Imported catalog record","sourceFetchedAt":null,"sourceSnapshotStatus":"not_synced","provenance":{"catalog":{"name":"Imported catalog record","url":null,"evidenceClass":"catalog fact","fetchedAt":null,"sourceUrl":null},"pricing":{"name":"Not reported","url":null,"evidenceClass":"catalog fact","observedAt":null,"sourceUrl":null},"metrics":{"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.992023+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":null,"catalogSourceUrl":null,"sourceUrl":null,"sourceUpdatedAt":{},"updated":"2026-08-25","releaseDate":null,"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":21,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"claude-3-opus","name":"Claude 3 Opus","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":null,"knowledgeCutoff":null,"license":null,"modalities":["Text"],"contextWindow":null,"maxOutputTokens":null,"apiAvailable":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Imported catalog record","url":null,"evidenceClass":"catalog fact","fetchedAt":null,"sourceUrl":null},"pricing":{"name":"Not reported","url":null,"evidenceClass":"catalog fact","observedAt":null,"sourceUrl":null},"metrics":{"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.992023+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"gpqa-diamond":95.4,"reasoning":95.4},"provenance":{"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.992023+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"}},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"gemini-3-pro","slug":"gemini-3-pro","canonicalId":"gemini-3-pro","name":"Gemini 3 Pro","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text"],"context_length":null,"context":null,"contextWindow":null,"maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":null,"completion":null},"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"price":"N/A","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":1,"overallScoreInputs":["overall"],"overallScoreMissing":["coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{"humanity-s-last-exam":45.8,"overall":45.8},"benchmarkProvenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.941397+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-09-15","source":"Imported catalog record","sourceName":"Imported catalog record","sourceFetchedAt":null,"sourceSnapshotStatus":"not_synced","provenance":{"catalog":{"name":"Imported catalog record","url":null,"evidenceClass":"catalog fact","fetchedAt":null,"sourceUrl":null},"pricing":{"name":"Not reported","url":null,"evidenceClass":"catalog fact","observedAt":null,"sourceUrl":null},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.941397+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":null,"catalogSourceUrl":null,"sourceUrl":null,"sourceUpdatedAt":{},"updated":"2026-08-25","releaseDate":null,"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":22,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"gemini-3-pro","name":"Gemini 3 Pro","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":null,"knowledgeCutoff":null,"license":null,"modalities":["Text"],"contextWindow":null,"maxOutputTokens":null,"apiAvailable":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Imported catalog record","url":null,"evidenceClass":"catalog fact","fetchedAt":null,"sourceUrl":null},"pricing":{"name":"Not reported","url":null,"evidenceClass":"catalog fact","observedAt":null,"sourceUrl":null},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.941397+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"humanity-s-last-exam":45.8,"overall":45.8},"provenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.941397+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"grok-4","slug":"grok-4","canonicalId":"grok-4","name":"Grok 4","provider":"xAI","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text"],"context_length":null,"context":null,"contextWindow":null,"maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":null,"completion":null},"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"price":"N/A","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":1,"overallScoreInputs":["overall"],"overallScoreMissing":["coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{"humanity-s-last-exam":25.4,"overall":25.4},"benchmarkProvenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T17:01:36.740789+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-08-25","source":"Imported catalog record","sourceName":"Imported catalog record","sourceFetchedAt":null,"sourceSnapshotStatus":"not_synced","provenance":{"catalog":{"name":"Imported catalog record","url":null,"evidenceClass":"catalog fact","fetchedAt":null,"sourceUrl":null},"pricing":{"name":"Not reported","url":null,"evidenceClass":"catalog fact","observedAt":null,"sourceUrl":null},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T17:01:36.740789+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":null,"catalogSourceUrl":null,"sourceUrl":null,"sourceUpdatedAt":{},"updated":"2026-08-25","releaseDate":null,"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=x.ai&sz=64","catalogRank":23,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"grok-4","name":"Grok 4","provider":"xAI","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":null,"knowledgeCutoff":null,"license":null,"modalities":["Text"],"contextWindow":null,"maxOutputTokens":null,"apiAvailable":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Imported catalog record","url":null,"evidenceClass":"catalog fact","fetchedAt":null,"sourceUrl":null},"pricing":{"name":"Not reported","url":null,"evidenceClass":"catalog fact","observedAt":null,"sourceUrl":null},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T17:01:36.740789+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"humanity-s-last-exam":25.4,"overall":25.4},"provenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T17:01:36.740789+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"gpt-5-6-luna","slug":"gpt-5-6-luna","canonicalId":"gpt-5-6-luna","name":"GPT-5.6 Luna","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.6-luna-20260709","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":2e-7,"completion":0.0000012},"inputPrice":0.19999999999999998,"outputPrice":1.2,"cachedInputPrice":null,"price":"$0.20","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":37.3,"coding":71.4,"agents":42.1,"speed":null,"latency":null,"benchmarkScores":{"swe-bench-verified":93,"coding":93},"benchmarkProvenance":{"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.803982+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"}},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-luna","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-luna","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":24,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"gpt-5-6-luna","name":"GPT-5.6 Luna","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.6-luna-20260709","releaseDate":{},"knowledgeCutoff":{},"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.19999999999999998,"outputPrice":1.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{"swe-bench-verified":93,"coding":93},"provenance":{"swe-bench-verified":{"url":"/benchmarks/swe-bench-verified","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.803982+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/swe-bench-verified"}},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"gemini-3-5-flash","slug":"gemini-3-5-flash","canonicalId":"gemini-3-5-flash","name":"Gemini 3.5 Flash","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-3.5-flash-20260519","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":0.0000015,"completion":0.000009},"inputPrice":1.5,"outputPrice":9,"cachedInputPrice":null,"price":"$1.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":1,"overallScoreInputs":["overall"],"overallScoreMissing":["coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":33.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{"humanity-s-last-exam":40.2,"overall":40.2},"benchmarkProvenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.767653+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-08-25","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.767653+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":25,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"gemini-3-5-flash","name":"Gemini 3.5 Flash","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-3.5-flash-20260519","releaseDate":{},"knowledgeCutoff":{},"license":null,"modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.5,"outputPrice":9,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.767653+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"humanity-s-last-exam":40.2,"overall":40.2},"provenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.767653+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-5-pro","slug":"openai-gpt-5-5-pro","canonicalId":"openai-gpt-5-5-pro","name":"GPT-5.5 Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.5-pro-20260423","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00003,"completion":0.00018},"inputPrice":30,"outputPrice":180,"cachedInputPrice":null,"price":"$30.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":1,"overallScoreInputs":["overall"],"overallScoreMissing":["coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{"humanity-s-last-exam":43.1,"overall":43.1},"benchmarkProvenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.9629+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-09-15","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.9629+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.5-pro","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.5-pro","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":26,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-5-pro","name":"GPT-5.5 Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.5-pro-20260423","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":30,"outputPrice":180,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.9629+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"humanity-s-last-exam":43.1,"overall":43.1},"provenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-09-15T19:16:02.9629+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-opus-4-7","slug":"anthropic-claude-opus-4-7","canonicalId":"anthropic-claude-opus-4-7","name":"Claude Opus 4.7","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4.7-opus-20260416","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000005,"completion":0.000025},"inputPrice":5,"outputPrice":25,"cachedInputPrice":null,"price":"$5.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":1,"overallScoreInputs":["reasoning"],"overallScoreMissing":["overall","coding","agents","computer_use","browsing","terminal"],"reasoning":94.2,"coding":73.6,"agents":38.6,"speed":null,"latency":null,"benchmarkScores":{"gpqa-diamond":94.2,"reasoning":94.2},"benchmarkProvenance":{"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-08-25T17:01:36.787434+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-08-25","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T17:01:36.787434+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":27,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-opus-4-7","name":"Claude Opus 4.7","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4.7-opus-20260416","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":5,"outputPrice":25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{"reasoning":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T17:01:36.787434+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"gpqa-diamond":94.2,"reasoning":94.2},"provenance":{"gpqa-diamond":{"url":"/benchmarks/gpqa-diamond","name":"Benchmark registry","observedAt":"2026-08-25T17:01:36.787434+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/gpqa-diamond"}},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"claude-sonnet-4-6","slug":"claude-sonnet-4-6","canonicalId":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4.6-sonnet-20260217","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000003,"completion":0.000015},"inputPrice":3,"outputPrice":15,"cachedInputPrice":null,"price":"$3.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":30.1,"coding":63,"agents":31.8,"speed":null,"latency":null,"benchmarkScores":{"osworld-verified":78.5,"computer_use":78.5},"benchmarkProvenance":{"osworld-verified":{"url":"/benchmarks/osworld","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.164995+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/osworld"}},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":28,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4.6-sonnet-20260217","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":3,"outputPrice":15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{"osworld-verified":78.5,"computer_use":78.5},"provenance":{"osworld-verified":{"url":"/benchmarks/osworld","name":"Benchmark registry","observedAt":"2026-09-15T19:16:03.164995+00:00","evidenceClass":"independent evaluator","sourceUrl":"/benchmarks/osworld"}},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"claude-opus-4-6","slug":"claude-opus-4-6","canonicalId":"claude-opus-4-6","name":"Claude Opus 4.6","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4.6-opus-20260205","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000005,"completion":0.000025},"inputPrice":5,"outputPrice":25,"cachedInputPrice":null,"price":"$5.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":1,"overallScoreInputs":["overall"],"overallScoreMissing":["coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":31.9,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{"humanity-s-last-exam":40,"overall":40},"benchmarkProvenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.782371+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-08-25","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.782371+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":29,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"claude-opus-4-6","name":"Claude Opus 4.6","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4.6-opus-20260205","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":5,"outputPrice":25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.782371+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"humanity-s-last-exam":40,"overall":40},"provenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.782371+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"gpt-5","slug":"gpt-5","canonicalId":"gpt-5","name":"GPT-5","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5-2025-08-07","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00000125,"completion":0.00001},"inputPrice":1.25,"outputPrice":10,"cachedInputPrice":null,"price":"$1.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":1,"overallScoreInputs":["overall"],"overallScoreMissing":["coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":23,"coding":37.8,"agents":0,"speed":null,"latency":null,"benchmarkScores":{"humanity-s-last-exam":35.2,"overall":35.2},"benchmarkProvenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.791984+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-08-25","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.791984+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":30,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"gpt-5","name":"GPT-5","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5-2025-08-07","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.25,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.791984+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"humanity-s-last-exam":35.2,"overall":35.2},"provenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.791984+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"gpt-oss-120b","slug":"gpt-oss-120b","canonicalId":"gpt-oss-120b","name":"gpt-oss-120b","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-oss-120b","modalities":["Text","Tools","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":1.5e-7,"completion":6e-7},"inputPrice":0.15,"outputPrice":0.6,"cachedInputPrice":null,"price":"$0.15","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":1,"overallScoreInputs":["overall"],"overallScoreMissing":["coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":11.6,"coding":30.4,"agents":3.7,"speed":null,"latency":null,"benchmarkScores":{"humanity-s-last-exam":14.9,"overall":14.9},"benchmarkProvenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.590565+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-08-25","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.590565+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-oss-120b","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-oss-120b","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":31,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"gpt-oss-120b","name":"gpt-oss-120b","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-oss-120b","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"131072","maxOutputTokens":"65536","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.15,"outputPrice":0.6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.590565+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"humanity-s-last-exam":14.9,"overall":14.9},"provenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.590565+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"gpt-oss-20b","slug":"gpt-oss-20b","canonicalId":"gpt-oss-20b","name":"gpt-oss-20b","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-oss-20b","modalities":["Text","Tools","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":1.8e-8,"completion":9e-8},"inputPrice":0.018,"outputPrice":0.09,"cachedInputPrice":null,"price":"$0.02","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":1,"overallScoreInputs":["overall"],"overallScoreMissing":["coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":10,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{"humanity-s-last-exam":10.9,"overall":10.9},"benchmarkProvenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.599411+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-08-25","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.599411+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-oss-20b","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-oss-20b","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":32,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"gpt-oss-20b","name":"gpt-oss-20b","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-oss-20b","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"131072","maxOutputTokens":"32768","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.018,"outputPrice":0.09,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.599411+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"humanity-s-last-exam":10.9,"overall":10.9},"provenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-08-25T09:15:24.599411+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-r1","slug":"deepseek-r1","canonicalId":"deepseek-r1","name":"R1","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"deepseek/deepseek-r1","modalities":["Text","Tools","Reasoning"],"context_length":"64000","context":"64000","contextWindow":"64000","maxOutputTokens":"16000","apiAvailable":true,"pricing":{"prompt":7e-7,"completion":0.0000025},"inputPrice":0.7,"outputPrice":2.5,"cachedInputPrice":null,"price":"$0.70","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":1,"overallScoreInputs":["overall"],"overallScoreMissing":["coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":11.4,"coding":24.6,"agents":1.1,"speed":null,"latency":null,"benchmarkScores":{"humanity-s-last-exam":8.6,"overall":8.6},"benchmarkProvenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.837491+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"benchmarkSource":"/methodology","benchmarkUpdated":"2026-10-14","source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.837491+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":33,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-r1","name":"R1","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"deepseek/deepseek-r1","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"64000","maxOutputTokens":"16000","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.7,"outputPrice":2.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{"overall":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.837491+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"fields":{}}},"publishedBenchmarks":{"scores":{"humanity-s-last-exam":8.6,"overall":8.6},"provenance":{"humanity-s-last-exam":{"url":"/methodology","name":"Benchmark registry","observedAt":"2026-10-14T02:26:02.837491+00:00","evidenceClass":"independent evaluator","sourceUrl":"/methodology"}},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-4-argon","slug":"google-gemini-4-argon","canonicalId":"google-gemini-4-argon","name":"Gemini 4 Argon","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemini-4-argon-20261013","modalities":["Audio","File","Image","Text","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.00001},"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":52.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":34,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-4-argon","name":"Gemini 4 Argon","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemini-4-argon-20261013","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Audio","File","Image","Text","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-4-argon-batch","slug":"google-gemini-4-argon-batch","canonicalId":"google-gemini-4-argon-batch","name":"Gemini 4 Argon (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-4-argon-20261013","modalities":["Audio","File","Image","Text","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000005},"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":52.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":35,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-4-argon-batch","name":"Gemini 4 Argon (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-4-argon-20261013","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Audio","File","Image","Text","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"liquid-lfm-2-5-24b-a2b","slug":"liquid-lfm-2-5-24b-a2b","canonicalId":"liquid-lfm-2-5-24b-a2b","name":"LFM2.5-24B-A2B","provider":"Liquid AI","family":null,"status":"active","variantType":"base","modelVersion":"liquid/lfm-2.5-24b-a2b-20261012","modalities":["Text","Tools","Reasoning"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"8192","apiAvailable":true,"pricing":{"prompt":5e-8,"completion":7e-7},"inputPrice":0.049999999999999996,"outputPrice":0.7,"cachedInputPrice":null,"price":"$0.05","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"https://www.liquid.ai/liquid-foundation-models","catalogSourceUrl":"/sources","sourceUrl":"https://www.liquid.ai/liquid-foundation-models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":36,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"liquid-lfm-2-5-24b-a2b","name":"LFM2.5-24B-A2B","provider":"Liquid AI","family":null,"status":"active","variantType":"base","modelVersion":"liquid/lfm-2.5-24b-a2b-20261012","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"128000","maxOutputTokens":"8192","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.049999999999999996,"outputPrice":0.7,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"scaledown-extract","slug":"scaledown-extract","canonicalId":"scaledown-extract","name":"Extract","provider":"ScaleDown","family":null,"status":"active","variantType":"base","modelVersion":"scaledown/extract-20260928","modalities":["Text","Image","File"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"900000","apiAvailable":true,"pricing":{"prompt":4e-8,"completion":0},"inputPrice":0.04,"outputPrice":0,"cachedInputPrice":null,"price":"$0.04","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":null,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":null,"catalogRank":37,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"scaledown-extract","name":"Extract","provider":"ScaleDown","family":null,"status":"active","variantType":"base","modelVersion":"scaledown/extract-20260928","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File"],"contextWindow":"1000000","maxOutputTokens":"900000","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":null,"promptCaching":false,"fineTuning":false,"inputPrice":0.04,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"scaledown-summarize","slug":"scaledown-summarize","canonicalId":"scaledown-summarize","name":"Summarize","provider":"ScaleDown","family":null,"status":"active","variantType":"base","modelVersion":"scaledown/summarize-20260928","modalities":["Text","Image","File"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"4000","apiAvailable":true,"pricing":{"prompt":4e-8,"completion":0},"inputPrice":0.04,"outputPrice":0,"cachedInputPrice":null,"price":"$0.04","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":null,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":null,"catalogRank":38,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"scaledown-summarize","name":"Summarize","provider":"ScaleDown","family":null,"status":"active","variantType":"base","modelVersion":"scaledown/summarize-20260928","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File"],"contextWindow":"1000000","maxOutputTokens":"4000","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":null,"promptCaching":false,"fineTuning":false,"inputPrice":0.04,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"unbiased-pareto-26-9","slug":"unbiased-pareto-26-9","canonicalId":"unbiased-pareto-26-9","name":"Pareto 26.9","provider":"Unbiased","family":null,"status":"active","variantType":"base","modelVersion":"unbiased/pareto-26.9-20260917","modalities":["Text","Image","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.0000075},"inputPrice":2.5,"outputPrice":7.5,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":null,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":null,"catalogRank":39,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"unbiased-pareto-26-9","name":"Pareto 26.9","provider":"Unbiased","family":null,"status":"active","variantType":"base","modelVersion":"unbiased/pareto-26.9-20260917","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Tools"],"contextWindow":"262144","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":null,"promptCaching":true,"fineTuning":false,"inputPrice":2.5,"outputPrice":7.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"unbiased-pareto-latest","slug":"unbiased-pareto-latest","canonicalId":"unbiased-pareto-latest","name":"Pareto Latest","provider":"Unbiased","family":null,"status":"active","variantType":"base","modelVersion":"~unbiased/pareto-latest","modalities":["Text","Image","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.0000075},"inputPrice":2.5,"outputPrice":7.5,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":null,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":null,"catalogRank":40,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"unbiased-pareto-latest","name":"Pareto Latest","provider":"Unbiased","family":null,"status":"active","variantType":"base","modelVersion":"~unbiased/pareto-latest","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Tools"],"contextWindow":"262144","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":null,"promptCaching":true,"fineTuning":false,"inputPrice":2.5,"outputPrice":7.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"meta-muse-wonder","slug":"meta-muse-wonder","canonicalId":"meta-muse-wonder","name":"Muse Wonder","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta/muse-wonder-20261012","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":0.000004,"completion":0.00002},"inputPrice":4,"outputPrice":20,"cachedInputPrice":null,"price":"$4.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}},"officialUrl":"https://www.llama.com/models/","catalogSourceUrl":"https://ai.meta.com/","sourceUrl":"https://www.llama.com/models/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=meta.com&sz=64","catalogRank":41,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"meta-muse-wonder","name":"Muse Wonder","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta/muse-wonder-20261012","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":4,"outputPrice":20,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"stepfun-step-5-preview","slug":"stepfun-step-5-preview","canonicalId":"stepfun-step-5-preview","name":"Step 5 Preview","provider":"StepFun","family":null,"status":"active","variantType":"preview","modelVersion":"stepfun/step-5-preview-20261008","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"64000","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.0000027},"inputPrice":1,"outputPrice":2.7,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://stepfun.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://stepfun.com/"},"pricing":{"name":"Provider source","url":"https://stepfun.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://stepfun.com/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://stepfun.com/","sourceUrl":"https://stepfun.com/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=stepfun.com&sz=64","catalogRank":42,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"stepfun-step-5-preview","name":"Step 5 Preview","provider":"StepFun","family":null,"status":"active","variantType":"preview","modelVersion":"stepfun/step-5-preview-20261008","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"64000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":2.7,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://stepfun.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://stepfun.com/"},"pricing":{"name":"Provider source","url":"https://stepfun.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://stepfun.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-haiku-5-5","slug":"anthropic-claude-haiku-5-5","canonicalId":"anthropic-claude-haiku-5-5","name":"Claude Haiku 5.5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-haiku-5.5-20261007","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":5e-7},"inputPrice":0.09999999999999999,"outputPrice":0.5,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":43.4,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":43,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-haiku-5-5","name":"Claude Haiku 5.5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-haiku-5.5-20261007","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-haiku-5-5-batch","slug":"anthropic-claude-haiku-5-5-batch","canonicalId":"anthropic-claude-haiku-5-5-batch","name":"Claude Haiku 5.5 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-haiku-5.5-20261007","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":5e-8,"completion":2.5e-7},"inputPrice":0.049999999999999996,"outputPrice":0.25,"cachedInputPrice":null,"price":"$0.05","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":43.4,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":44,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-haiku-5-5-batch","name":"Claude Haiku 5.5 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-haiku-5.5-20261007","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.049999999999999996,"outputPrice":0.25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-nano-banana-2-1","slug":"google-gemini-nano-banana-2-1","canonicalId":"google-gemini-nano-banana-2-1","name":"Nano Banana 2.1","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemini-nano-banana-2.1-20261006","modalities":["Image","Text","Tools","Reasoning"],"context_length":"65536","context":"65536","contextWindow":"65536","maxOutputTokens":"58982","apiAvailable":true,"pricing":{"prompt":0.0000015,"completion":0.0000075},"inputPrice":1.5,"outputPrice":7.5,"cachedInputPrice":null,"price":"$1.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":45,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-nano-banana-2-1","name":"Nano Banana 2.1","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemini-nano-banana-2.1-20261006","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Image","Text","Tools","Reasoning"],"contextWindow":"65536","maxOutputTokens":"58982","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":1.5,"outputPrice":7.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-mistral-large-4-0","slug":"mistralai-mistral-large-4-0","canonicalId":"mistralai-mistral-large-4-0","name":"Mistral Large 4","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-large-4-0-20261006","modalities":["Text","Image","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"262144","apiAvailable":true,"pricing":{"prompt":6.8e-7,"completion":0.00000209},"inputPrice":0.6799999999999999,"outputPrice":2.09,"cachedInputPrice":null,"price":"$0.68","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":46,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-mistral-large-4-0","name":"Mistral Large 4","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-large-4-0-20261006","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"262144","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.6799999999999999,"outputPrice":2.09,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"inclusionai-ling-3-1-flash","slug":"inclusionai-ling-3-1-flash","canonicalId":"inclusionai-ling-3-1-flash","name":"Ling 3.1 Flash","provider":"InclusionAI","family":null,"status":"active","variantType":"fast","modelVersion":"inclusionai/ling-3.1-flash-20261002","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":7.5e-8,"completion":2.25e-7},"inputPrice":0.075,"outputPrice":0.22499999999999998,"cachedInputPrice":null,"price":"$0.07","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":41.1,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-fp8","catalogSourceUrl":"/sources","sourceUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-fp8","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":null,"catalogRank":47,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"inclusionai-ling-3-1-flash","name":"Ling 3.1 Flash","provider":"InclusionAI","family":null,"status":"active","variantType":"fast","modelVersion":"inclusionai/ling-3.1-flash-20261002","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.075,"outputPrice":0.22499999999999998,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"apodex-apodex-1-1-mini-free","slug":"apodex-apodex-1-1-mini-free","canonicalId":"apodex-apodex-1-1-mini-free","name":"Apodex 1.1 Mini (free)","provider":"Apodex","family":null,"status":"active","variantType":"free","modelVersion":"apodex/apodex-1.1-mini-20261001","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-13","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":null,"catalogRank":48,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"apodex-apodex-1-1-mini-free","name":"Apodex 1.1 Mini (free)","provider":"Apodex","family":null,"status":"active","variantType":"free","modelVersion":"apodex/apodex-1.1-mini-20261001","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"unbiased-pareto-26-10-preview","slug":"unbiased-pareto-26-10-preview","canonicalId":"unbiased-pareto-26-10-preview","name":"Pareto 26.10 Preview","provider":"Unbiased","family":null,"status":"active","variantType":"preview","modelVersion":"unbiased/pareto-26.10-preview-20260929","modalities":["Text","Image","Tools"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":8e-7,"completion":0.0000032},"inputPrice":0.7999999999999999,"outputPrice":3.1999999999999997,"cachedInputPrice":null,"price":"$0.80","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":null,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":null,"catalogRank":49,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"unbiased-pareto-26-10-preview","name":"Pareto 26.10 Preview","provider":"Unbiased","family":null,"status":"active","variantType":"preview","modelVersion":"unbiased/pareto-26.10-preview-20260929","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Tools"],"contextWindow":"1048576","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":null,"promptCaching":true,"fineTuning":false,"inputPrice":0.7999999999999999,"outputPrice":3.1999999999999997,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-6-1-sol","slug":"openai-gpt-6-1-sol","canonicalId":"openai-gpt-6-1-sol","name":"GPT-6.1 Sol","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-6.1-sol-20260929","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.00001},"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":51.8,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-6.1-sol","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-6.1-sol","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":50,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-6-1-sol","name":"GPT-6.1 Sol","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-6.1-sol-20260929","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-6-1-sol-batch","slug":"openai-gpt-6-1-sol-batch","canonicalId":"openai-gpt-6-1-sol-batch","name":"GPT-6.1 Sol (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-6.1-sol-20260929","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000005},"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":51.8,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-6.1-sol:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-6.1-sol:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":51,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-6-1-sol-batch","name":"GPT-6.1 Sol (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-6.1-sol-20260929","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-6-1-sol-pro","slug":"openai-gpt-6-1-sol-pro","canonicalId":"openai-gpt-6-1-sol-pro","name":"GPT-6.1 Sol Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-6.1-sol-pro-20260929","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.00001},"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-6.1-sol-pro","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-6.1-sol-pro","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":52,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-6-1-sol-pro","name":"GPT-6.1 Sol Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-6.1-sol-pro-20260929","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-6-1-sol-pro-batch","slug":"openai-gpt-6-1-sol-pro-batch","canonicalId":"openai-gpt-6-1-sol-pro-batch","name":"GPT-6.1 Sol Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-6.1-sol-pro-20260929","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000005},"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-6.1-sol-pro:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-6.1-sol-pro:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":53,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-6-1-sol-pro-batch","name":"GPT-6.1 Sol Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-6.1-sol-pro-20260929","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-sonnet-5-5","slug":"anthropic-claude-sonnet-5-5","canonicalId":"anthropic-claude-sonnet-5-5","name":"Claude Sonnet 5.5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-sonnet-5.5-20260928","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.00001},"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":56,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":54,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-sonnet-5-5","name":"Claude Sonnet 5.5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-sonnet-5.5-20260928","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-sonnet-5-5-batch","slug":"anthropic-claude-sonnet-5-5-batch","canonicalId":"anthropic-claude-sonnet-5-5-batch","name":"Claude Sonnet 5.5 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-sonnet-5.5-20260928","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000005},"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":56,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":55,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-sonnet-5-5-batch","name":"Claude Sonnet 5.5 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-sonnet-5.5-20260928","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"perceptron-perceptron-mk1-5","slug":"perceptron-perceptron-mk1-5","canonicalId":"perceptron-perceptron-mk1-5","name":"Perceptron Mk1.5","provider":"Perceptron","family":null,"status":"active","variantType":"base","modelVersion":"perceptron/perceptron-mk1.5-20260925","modalities":["Text","Image","Video","Audio","Tools","Reasoning"],"context_length":"36864","context":"36864","contextWindow":"36864","maxOutputTokens":"8192","apiAvailable":true,"pricing":{"prompt":1.5e-7,"completion":0.0000015},"inputPrice":0.15,"outputPrice":1.5,"cachedInputPrice":null,"price":"$0.15","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":null,"catalogRank":56,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"perceptron-perceptron-mk1-5","name":"Perceptron Mk1.5","provider":"Perceptron","family":null,"status":"active","variantType":"base","modelVersion":"perceptron/perceptron-mk1.5-20260925","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Video","Audio","Tools","Reasoning"],"contextWindow":"36864","maxOutputTokens":"8192","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.15,"outputPrice":1.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"typesafe-jev-router","slug":"typesafe-jev-router","canonicalId":"typesafe-jev-router","name":"Jev Router","provider":"TypeSafe","family":null,"status":"active","variantType":"router","modelVersion":"typesafe/jev-router","modalities":["Audio","File","Image","Text","Video","Tools"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":null,"apiAvailable":true,"pricing":{"prompt":null,"completion":null},"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"price":"N/A","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":null,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":null,"catalogRank":57,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"typesafe-jev-router","name":"Jev Router","provider":"TypeSafe","family":null,"status":"active","variantType":"router","modelVersion":"typesafe/jev-router","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Audio","File","Image","Text","Video","Tools"],"contextWindow":"1000000","maxOutputTokens":null,"apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":null,"promptCaching":false,"fineTuning":false,"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"fireworks-ember-1","slug":"fireworks-ember-1","canonicalId":"fireworks-ember-1","name":"Ember-1","provider":"Fireworks","family":null,"status":"active","variantType":"base","modelVersion":"fireworks/ember-1-20260923","modalities":["Text","Image","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":0.000003,"completion":0.000015},"inputPrice":3,"outputPrice":15,"cachedInputPrice":null,"price":"$3.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":null,"catalogRank":58,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"fireworks-ember-1","name":"Ember-1","provider":"Fireworks","family":null,"status":"active","variantType":"base","modelVersion":"fireworks/ember-1-20260923","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":3,"outputPrice":15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"aion-labs-aion-3-5","slug":"aion-labs-aion-3-5","canonicalId":"aion-labs-aion-3-5","name":"Aion 3.5","provider":"AionLabs","family":null,"status":"active","variantType":"base","modelVersion":"aion-labs/aion-3.5-20260923","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":0.000003,"completion":0.000006},"inputPrice":3,"outputPrice":6,"cachedInputPrice":null,"price":"$3.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aionlabs.ai/"},"pricing":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aionlabs.ai/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://aionlabs.ai/","sourceUrl":"https://aionlabs.ai/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=aionlabs.ai&sz=64","catalogRank":59,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"aion-labs-aion-3-5","name":"Aion 3.5","provider":"AionLabs","family":null,"status":"active","variantType":"base","modelVersion":"aion-labs/aion-3.5-20260923","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":3,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aionlabs.ai/"},"pricing":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aionlabs.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"aion-labs-aion-3-5-mini","slug":"aion-labs-aion-3-5-mini","canonicalId":"aion-labs-aion-3-5-mini","name":"Aion 3.5 Mini","provider":"AionLabs","family":null,"status":"active","variantType":"fast","modelVersion":"aion-labs/aion-3.5-mini-20260923","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":7e-7,"completion":0.0000014},"inputPrice":0.7,"outputPrice":1.4,"cachedInputPrice":null,"price":"$0.70","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aionlabs.ai/"},"pricing":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aionlabs.ai/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://aionlabs.ai/","sourceUrl":"https://aionlabs.ai/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=aionlabs.ai&sz=64","catalogRank":60,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"aion-labs-aion-3-5-mini","name":"Aion 3.5 Mini","provider":"AionLabs","family":null,"status":"active","variantType":"fast","modelVersion":"aion-labs/aion-3.5-mini-20260923","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.7,"outputPrice":1.4,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aionlabs.ai/"},"pricing":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aionlabs.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-8-max-prime","slug":"qwen-qwen3-8-max-prime","canonicalId":"qwen-qwen3-8-max-prime","name":"Qwen3.8 Max Prime","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.8-max-prime-20260923","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":0.000004,"completion":0.000012},"inputPrice":4,"outputPrice":12,"cachedInputPrice":null,"price":"$4.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":61,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-8-max-prime","name":"Qwen3.8 Max Prime","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.8-max-prime-20260923","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":4,"outputPrice":12,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"upstage-solar-mini4","slug":"upstage-solar-mini4","canonicalId":"upstage-solar-mini4","name":"Solar Mini 4","provider":"Upstage","family":null,"status":"active","variantType":"fast","modelVersion":"upstage/solar-mini4-20260922","modalities":["Text","Tools","Reasoning"],"context_length":"524288","context":"524288","contextWindow":"524288","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":5e-8,"completion":2e-7},"inputPrice":0.049999999999999996,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"price":"$0.05","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":24.1,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://upstage.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://upstage.ai/"},"pricing":{"name":"Provider source","url":"https://upstage.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://upstage.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.upstage.ai/docs/apis/chat","catalogSourceUrl":"https://upstage.ai/","sourceUrl":"https://developers.upstage.ai/docs/apis/chat","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=upstage.ai&sz=64","catalogRank":62,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"upstage-solar-mini4","name":"Solar Mini 4","provider":"Upstage","family":null,"status":"active","variantType":"fast","modelVersion":"upstage/solar-mini4-20260922","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Tools","Reasoning"],"contextWindow":"524288","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.049999999999999996,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://upstage.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://upstage.ai/"},"pricing":{"name":"Provider source","url":"https://upstage.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://upstage.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-5-3-prime","slug":"z-ai-glm-5-3-prime","canonicalId":"z-ai-glm-5-3-prime","name":"GLM 5.3 Prime","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-5.3-prime-20260921","modalities":["Text","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":0.0000028,"completion":0.0000088},"inputPrice":2.8,"outputPrice":8.8,"cachedInputPrice":null,"price":"$2.80","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":63,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-5-3-prime","name":"GLM 5.3 Prime","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-5.3-prime-20260921","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2.8,"outputPrice":8.8,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-opus-5-5","slug":"anthropic-claude-opus-5-5","canonicalId":"anthropic-claude-opus-5-5","name":"Claude Opus 5.5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-opus-5.5-20260921","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000004,"completion":0.00002},"inputPrice":4,"outputPrice":20,"cachedInputPrice":null,"price":"$4.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":57.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":64,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-opus-5-5","name":"Claude Opus 5.5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-opus-5.5-20260921","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":4,"outputPrice":20,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-opus-5-5-batch","slug":"anthropic-claude-opus-5-5-batch","canonicalId":"anthropic-claude-opus-5-5-batch","name":"Claude Opus 5.5 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-opus-5.5-20260921","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.00001},"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":57.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":65,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-opus-5-5-batch","name":"Claude Opus 5.5 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-opus-5.5-20260921","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-6-luna","slug":"openai-gpt-6-luna","canonicalId":"openai-gpt-6-luna","name":"GPT-6 Luna","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-6-luna-20260922","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":5e-7},"inputPrice":0.09999999999999999,"outputPrice":0.5,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":38.1,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-6-luna","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-6-luna","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":66,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-6-luna","name":"GPT-6 Luna","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-6-luna-20260922","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-6-luna-batch","slug":"openai-gpt-6-luna-batch","canonicalId":"openai-gpt-6-luna-batch","name":"GPT-6 Luna (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-6-luna-20260922","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":5e-8,"completion":2.5e-7},"inputPrice":0.049999999999999996,"outputPrice":0.25,"cachedInputPrice":null,"price":"$0.05","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":38.1,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-6-luna:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-6-luna:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":67,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-6-luna-batch","name":"GPT-6 Luna (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-6-luna-20260922","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.049999999999999996,"outputPrice":0.25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-6-luna-pro","slug":"openai-gpt-6-luna-pro","canonicalId":"openai-gpt-6-luna-pro","name":"GPT-6 Luna Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-6-luna-pro-20260922","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":5e-7},"inputPrice":0.09999999999999999,"outputPrice":0.5,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-6-luna-pro","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-6-luna-pro","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":68,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-6-luna-pro","name":"GPT-6 Luna Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-6-luna-pro-20260922","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-6-luna-pro-batch","slug":"openai-gpt-6-luna-pro-batch","canonicalId":"openai-gpt-6-luna-pro-batch","name":"GPT-6 Luna Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-6-luna-pro-20260922","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":5e-8,"completion":2.5e-7},"inputPrice":0.049999999999999996,"outputPrice":0.25,"cachedInputPrice":null,"price":"$0.05","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-6-luna-pro:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-6-luna-pro:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":69,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-6-luna-pro-batch","name":"GPT-6 Luna Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-6-luna-pro-20260922","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.049999999999999996,"outputPrice":0.25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-6-sol","slug":"openai-gpt-6-sol","canonicalId":"openai-gpt-6-sol","name":"GPT-6 Sol","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-6-sol-20260922","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.00001},"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":47.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-6-sol","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-6-sol","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":70,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-6-sol","name":"GPT-6 Sol","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-6-sol-20260922","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-6-sol-batch","slug":"openai-gpt-6-sol-batch","canonicalId":"openai-gpt-6-sol-batch","name":"GPT-6 Sol (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-6-sol-20260922","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000005},"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":47.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-6-sol:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-6-sol:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":71,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-6-sol-batch","name":"GPT-6 Sol (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-6-sol-20260922","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-6-sol-pro","slug":"openai-gpt-6-sol-pro","canonicalId":"openai-gpt-6-sol-pro","name":"GPT-6 Sol Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-6-sol-pro-20260922","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.00001},"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-6-sol-pro","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-6-sol-pro","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":72,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-6-sol-pro","name":"GPT-6 Sol Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-6-sol-pro-20260922","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-6-sol-pro-batch","slug":"openai-gpt-6-sol-pro-batch","canonicalId":"openai-gpt-6-sol-pro-batch","name":"GPT-6 Sol Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-6-sol-pro-20260922","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000005},"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-6-sol-pro:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-6-sol-pro:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":73,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-6-sol-pro-batch","name":"GPT-6 Sol Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-6-sol-pro-20260922","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"nvidia-switchyard","slug":"nvidia-switchyard","canonicalId":"nvidia-switchyard","name":"Switchyard","provider":"NVIDIA","family":null,"status":"active","variantType":"base","modelVersion":"nvidia/switchyard","modalities":["Text"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":null,"apiAvailable":true,"pricing":{"prompt":null,"completion":null},"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"price":"N/A","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}},"officialUrl":"https://build.nvidia.com/explore/discover","catalogSourceUrl":"https://nvidia.com/","sourceUrl":"https://build.nvidia.com/explore/discover","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":null,"structuredOutput":null,"webSearch":null,"reasoningCapability":null,"promptCaching":false,"fineTuning":null,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=nvidia.com&sz=64","catalogRank":74,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"nvidia-switchyard","name":"Switchyard","provider":"NVIDIA","family":null,"status":"active","variantType":"base","modelVersion":"nvidia/switchyard","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text"],"contextWindow":"1000000","maxOutputTokens":null,"apiAvailable":true,"openWeights":false,"toolCalling":null,"structuredOutput":null,"webSearch":null,"reasoningCapability":null,"promptCaching":false,"fineTuning":null,"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-8-omni-flash","slug":"qwen-qwen3-8-omni-flash","canonicalId":"qwen-qwen3-8-omni-flash","name":"Qwen3.8 Omni Flash","provider":"Qwen","family":null,"status":"active","variantType":"fast","modelVersion":"qwen/qwen3.8-omni-flash-20260918","modalities":["Text","Image","Audio","Video","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":1.5e-7,"completion":4.6999999999999995e-7},"inputPrice":0.15,"outputPrice":0.47,"cachedInputPrice":null,"price":"$0.15","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":75,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-8-omni-flash","name":"Qwen3.8 Omni Flash","provider":"Qwen","family":null,"status":"active","variantType":"fast","modelVersion":"qwen/qwen3.8-omni-flash-20260918","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Audio","Video","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.15,"outputPrice":0.47,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"x-ai-grok-4-7","slug":"x-ai-grok-4-7","canonicalId":"x-ai-grok-4-7","name":"Grok 4.7","provider":"xAI","family":null,"status":"active","variantType":"base","modelVersion":"x-ai/grok-4.7-20260916","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"500000","context":"500000","contextWindow":"500000","maxOutputTokens":"450000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000006},"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":46.4,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://x.ai/"},"pricing":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://x.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.x.ai/docs/models","catalogSourceUrl":"https://x.ai/","sourceUrl":"https://docs.x.ai/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=x.ai&sz=64","catalogRank":76,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"x-ai-grok-4-7","name":"Grok 4.7","provider":"xAI","family":null,"status":"active","variantType":"base","modelVersion":"x-ai/grok-4.7-20260916","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"500000","maxOutputTokens":"450000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://x.ai/"},"pricing":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://x.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"xiaomi-mimo-v2-6-flash","slug":"xiaomi-mimo-v2-6-flash","canonicalId":"xiaomi-mimo-v2-6-flash","name":"MiMo-V2.6-Flash","provider":"Xiaomi","family":null,"status":"active","variantType":"fast","modelVersion":"xiaomi/mimo-v2.6-flash-20260921","modalities":["Text","Image","Video","Audio","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":1.4e-7,"completion":2.8e-7},"inputPrice":0.14,"outputPrice":0.28,"cachedInputPrice":null,"price":"$0.14","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":37.9,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mi.com/"},"pricing":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mi.com/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://mi.com/","sourceUrl":"https://mi.com/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=mi.com&sz=64","catalogRank":77,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"xiaomi-mimo-v2-6-flash","name":"MiMo-V2.6-Flash","provider":"Xiaomi","family":null,"status":"active","variantType":"fast","modelVersion":"xiaomi/mimo-v2.6-flash-20260921","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Audio","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"131072","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.14,"outputPrice":0.28,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mi.com/"},"pricing":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mi.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"xiaomi-mimo-v2-6-pro","slug":"xiaomi-mimo-v2-6-pro","canonicalId":"xiaomi-mimo-v2-6-pro","name":"MiMo-V2.6-Pro","provider":"Xiaomi","family":null,"status":"active","variantType":"base","modelVersion":"xiaomi/mimo-v2.6-pro-20260921","modalities":["Text","Image","Video","Audio","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":4.35e-7,"completion":8.7e-7},"inputPrice":0.435,"outputPrice":0.87,"cachedInputPrice":null,"price":"$0.43","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":46.3,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mi.com/"},"pricing":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mi.com/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://mi.com/","sourceUrl":"https://mi.com/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=mi.com&sz=64","catalogRank":78,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"xiaomi-mimo-v2-6-pro","name":"MiMo-V2.6-Pro","provider":"Xiaomi","family":null,"status":"active","variantType":"base","modelVersion":"xiaomi/mimo-v2.6-pro-20260921","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Audio","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"131072","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.435,"outputPrice":0.87,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mi.com/"},"pricing":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mi.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"xiaomi-mimo-v2-6-pro-ultraspeed","slug":"xiaomi-mimo-v2-6-pro-ultraspeed","canonicalId":"xiaomi-mimo-v2-6-pro-ultraspeed","name":"MiMo-V2.6-Pro-UltraSpeed","provider":"Xiaomi","family":null,"status":"active","variantType":"base","modelVersion":"xiaomi/mimo-v2.6-pro-ultraspeed-20260921","modalities":["Text","Image","Video","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":0.00000435,"completion":0.0000087},"inputPrice":4.35,"outputPrice":8.7,"cachedInputPrice":null,"price":"$4.35","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mi.com/"},"pricing":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mi.com/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://mi.com/","sourceUrl":"https://mi.com/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=mi.com&sz=64","catalogRank":79,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"xiaomi-mimo-v2-6-pro-ultraspeed","name":"MiMo-V2.6-Pro-UltraSpeed","provider":"Xiaomi","family":null,"status":"active","variantType":"base","modelVersion":"xiaomi/mimo-v2.6-pro-ultraspeed-20260921","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Video","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":4.35,"outputPrice":8.7,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mi.com/"},"pricing":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mi.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"prism-ml-ternary-bonsai-2-27b","slug":"prism-ml-ternary-bonsai-2-27b","canonicalId":"prism-ml-ternary-bonsai-2-27b","name":"Ternary Bonsai 2 27B","provider":"PrismML","family":null,"status":"active","variantType":"base","modelVersion":"prism-ml/ternary-bonsai-2-27b-20260918","modalities":["Text","Image","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":7.5e-8,"completion":5e-7},"inputPrice":0.075,"outputPrice":0.5,"cachedInputPrice":null,"price":"$0.07","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":80,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"prism-ml-ternary-bonsai-2-27b","name":"Ternary Bonsai 2 27B","provider":"PrismML","family":null,"status":"active","variantType":"base","modelVersion":"prism-ml/ternary-bonsai-2-27b-20260918","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.075,"outputPrice":0.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-5-3-flashx","slug":"z-ai-glm-5-3-flashx","canonicalId":"z-ai-glm-5-3-flashx","name":"GLM 5.3 FlashX","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-5.3-flashx-20260918","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":3.7e-7,"completion":0.00000125},"inputPrice":0.37,"outputPrice":1.25,"cachedInputPrice":null,"price":"$0.37","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":81,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-5-3-flashx","name":"GLM 5.3 FlashX","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-5.3-flashx-20260918","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.37,"outputPrice":1.25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"typesafe-jev-latest","slug":"typesafe-jev-latest","canonicalId":"typesafe-jev-latest","name":"Jev Latest","provider":"TypeSafe","family":null,"status":"active","variantType":"base","modelVersion":"~typesafe/jev-latest","modalities":["Text"],"context_length":null,"context":null,"contextWindow":null,"maxOutputTokens":null,"apiAvailable":true,"pricing":{"prompt":null,"completion":null},"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"price":"N/A","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-09-17","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":null,"structuredOutput":null,"webSearch":null,"reasoningCapability":null,"promptCaching":false,"fineTuning":null,"lastVerifiedAt":{},"license":null,"providerIconUrl":null,"catalogRank":82,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"typesafe-jev-latest","name":"Jev Latest","provider":"TypeSafe","family":null,"status":"active","variantType":"base","modelVersion":"~typesafe/jev-latest","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text"],"contextWindow":null,"maxOutputTokens":null,"apiAvailable":true,"openWeights":false,"toolCalling":null,"structuredOutput":null,"webSearch":null,"reasoningCapability":null,"promptCaching":false,"fineTuning":null,"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"unbiased-pareto","slug":"unbiased-pareto","canonicalId":"unbiased-pareto","name":"Pareto","provider":"Unbiased","family":null,"status":"active","variantType":"base","modelVersion":"unbiased/pareto-20260917","modalities":["Text","Image","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.0000075},"inputPrice":2.5,"outputPrice":7.5,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-13","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":null,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":null,"catalogRank":83,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"unbiased-pareto","name":"Pareto","provider":"Unbiased","family":null,"status":"active","variantType":"base","modelVersion":"unbiased/pareto-20260917","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Tools"],"contextWindow":"262144","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":null,"promptCaching":true,"fineTuning":false,"inputPrice":2.5,"outputPrice":7.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"stealth-union-alpha","slug":"stealth-union-alpha","canonicalId":"stealth-union-alpha","name":"Union Alpha","provider":"Stealth","family":null,"status":"active","variantType":"base","modelVersion":"stealth/union-alpha","modalities":["Text","Image","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-09-17","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":null,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":null,"catalogRank":84,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"stealth-union-alpha","name":"Union Alpha","provider":"Stealth","family":null,"status":"active","variantType":"base","modelVersion":"stealth/union-alpha","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Tools"],"contextWindow":"262144","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":null,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-flash-latest","slug":"deepseek-deepseek-flash-latest","canonicalId":"deepseek-deepseek-flash-latest","name":"DeepSeek Flash Latest","provider":"DeepSeek","family":null,"status":"active","variantType":"fast","modelVersion":"~deepseek/deepseek-flash-latest","modalities":["Text","Image","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":3.69e-8,"completion":8.91e-7},"inputPrice":0.0369,"outputPrice":0.891,"cachedInputPrice":null,"price":"$0.04","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":85,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-flash-latest","name":"DeepSeek Flash Latest","provider":"DeepSeek","family":null,"status":"active","variantType":"fast","modelVersion":"~deepseek/deepseek-flash-latest","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.0369,"outputPrice":0.891,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-pro-latest","slug":"deepseek-deepseek-pro-latest","canonicalId":"deepseek-deepseek-pro-latest","name":"DeepSeek Pro Latest","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"~deepseek/deepseek-pro-latest","modalities":["Text","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"393216","apiAvailable":true,"pricing":{"prompt":2e-7,"completion":0.000006},"inputPrice":0.19999999999999998,"outputPrice":6,"cachedInputPrice":null,"price":"$0.20","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":86,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-pro-latest","name":"DeepSeek Pro Latest","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"~deepseek/deepseek-pro-latest","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"393216","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.19999999999999998,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"inference-net-schematron-v2-small","slug":"inference-net-schematron-v2-small","canonicalId":"inference-net-schematron-v2-small","name":"Schematron V2 Small","provider":"Inference.net","family":null,"status":"active","variantType":"base","modelVersion":"inference-net/schematron-v2-small-20260902","modalities":["Text"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"4096","apiAvailable":true,"pricing":{"prompt":5e-8,"completion":2.3e-7},"inputPrice":0.049999999999999996,"outputPrice":0.22999999999999998,"cachedInputPrice":null,"price":"$0.05","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":null,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":87,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"inference-net-schematron-v2-small","name":"Schematron V2 Small","provider":"Inference.net","family":null,"status":"active","variantType":"base","modelVersion":"inference-net/schematron-v2-small-20260902","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text"],"contextWindow":"128000","maxOutputTokens":"4096","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":null,"promptCaching":true,"fineTuning":false,"inputPrice":0.049999999999999996,"outputPrice":0.22999999999999998,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"inference-net-schematron-v2-turbo","slug":"inference-net-schematron-v2-turbo","canonicalId":"inference-net-schematron-v2-turbo","name":"Schematron V2 Turbo","provider":"Inference.net","family":null,"status":"active","variantType":"base","modelVersion":"inference-net/schematron-v2-turbo-20260902","modalities":["Text"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"8192","apiAvailable":true,"pricing":{"prompt":3e-8,"completion":1.5e-7},"inputPrice":0.03,"outputPrice":0.15,"cachedInputPrice":null,"price":"$0.03","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":null,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":88,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"inference-net-schematron-v2-turbo","name":"Schematron V2 Turbo","provider":"Inference.net","family":null,"status":"active","variantType":"base","modelVersion":"inference-net/schematron-v2-turbo-20260902","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text"],"contextWindow":"128000","maxOutputTokens":"8192","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":null,"promptCaching":true,"fineTuning":false,"inputPrice":0.03,"outputPrice":0.15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-astra-latest","slug":"openai-gpt-astra-latest","canonicalId":"openai-gpt-astra-latest","name":"GPT Astra Latest","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"~openai/gpt-astra-latest","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00001,"completion":0.00005},"inputPrice":10,"outputPrice":50,"cachedInputPrice":null,"price":"$10.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-astra-latest","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-astra-latest","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":89,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-astra-latest","name":"GPT Astra Latest","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"~openai/gpt-astra-latest","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":10,"outputPrice":50,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-luna-latest","slug":"openai-gpt-luna-latest","canonicalId":"openai-gpt-luna-latest","name":"GPT Luna Latest","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"~openai/gpt-luna-latest","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":5e-7},"inputPrice":0.09999999999999999,"outputPrice":0.5,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-luna-latest","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-luna-latest","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":90,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-luna-latest","name":"GPT Luna Latest","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"~openai/gpt-luna-latest","releaseDate":{},"knowledgeCutoff":{},"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-sol-latest","slug":"openai-gpt-sol-latest","canonicalId":"openai-gpt-sol-latest","name":"GPT Sol Latest","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"~openai/gpt-sol-latest","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.00001},"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-sol-latest","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-sol-latest","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":91,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-sol-latest","name":"GPT Sol Latest","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"~openai/gpt-sol-latest","releaseDate":{},"knowledgeCutoff":{},"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-terra-latest","slug":"openai-gpt-terra-latest","canonicalId":"openai-gpt-terra-latest","name":"GPT Terra Latest","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"~openai/gpt-terra-latest","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000012},"inputPrice":2,"outputPrice":12,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-terra-latest","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-terra-latest","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":92,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-terra-latest","name":"GPT Terra Latest","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"~openai/gpt-terra-latest","releaseDate":{},"knowledgeCutoff":{},"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":12,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"sakana-fugu-max","slug":"sakana-fugu-max","canonicalId":"sakana-fugu-max","name":"Fugu Max","provider":"Sakana","family":null,"status":"active","variantType":"base","modelVersion":"sakana/fugu-max-20260911","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000006},"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://sakana.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://sakana.ai/"},"pricing":{"name":"Provider source","url":"https://sakana.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://sakana.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://sakana.ai/namazu-api/","catalogSourceUrl":"https://sakana.ai/","sourceUrl":"https://sakana.ai/namazu-api/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=sakana.ai&sz=64","catalogRank":93,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"sakana-fugu-max","name":"Fugu Max","provider":"Sakana","family":null,"status":"active","variantType":"base","modelVersion":"sakana/fugu-max-20260911","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://sakana.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://sakana.ai/"},"pricing":{"name":"Provider source","url":"https://sakana.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://sakana.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"sakana-fugu-ultra-v2","slug":"sakana-fugu-ultra-v2","canonicalId":"sakana-fugu-ultra-v2","name":"Fugu Ultra v2","provider":"Sakana","family":null,"status":"active","variantType":"base","modelVersion":"sakana/fugu-ultra-v2-20260911","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000005,"completion":0.00003},"inputPrice":5,"outputPrice":30,"cachedInputPrice":null,"price":"$5.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://sakana.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://sakana.ai/"},"pricing":{"name":"Provider source","url":"https://sakana.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://sakana.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://sakana.ai/namazu-api/","catalogSourceUrl":"https://sakana.ai/","sourceUrl":"https://sakana.ai/namazu-api/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=sakana.ai&sz=64","catalogRank":94,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"sakana-fugu-ultra-v2","name":"Fugu Ultra v2","provider":"Sakana","family":null,"status":"active","variantType":"base","modelVersion":"sakana/fugu-ultra-v2-20260911","releaseDate":{},"knowledgeCutoff":{},"license":null,"modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":5,"outputPrice":30,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://sakana.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://sakana.ai/"},"pricing":{"name":"Provider source","url":"https://sakana.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://sakana.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-v4-1-flash","slug":"deepseek-deepseek-v4-1-flash","canonicalId":"deepseek-deepseek-v4-1-flash","name":"DeepSeek V4.1 Flash","provider":"DeepSeek","family":null,"status":"active","variantType":"fast","modelVersion":"deepseek/deepseek-v4.1-flash-20260910","modalities":["Text","Image","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":3.69e-8,"completion":8.91e-7},"inputPrice":0.0369,"outputPrice":0.891,"cachedInputPrice":null,"price":"$0.04","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":39.5,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":95,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-v4-1-flash","name":"DeepSeek V4.1 Flash","provider":"DeepSeek","family":null,"status":"active","variantType":"fast","modelVersion":"deepseek/deepseek-v4.1-flash-20260910","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.0369,"outputPrice":0.891,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-v4-1-flash-batch","slug":"deepseek-deepseek-v4-1-flash-batch","canonicalId":"deepseek-deepseek-v4-1-flash-batch","name":"DeepSeek V4.1 Flash (batch)","provider":"DeepSeek","family":null,"status":"active","variantType":"batch","modelVersion":"deepseek/deepseek-v4.1-flash-20260910","modalities":["Text","Image","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":1.12e-7,"completion":3.36e-7},"inputPrice":0.112,"outputPrice":0.33599999999999997,"cachedInputPrice":null,"price":"$0.11","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":39.5,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":96,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-v4-1-flash-batch","name":"DeepSeek V4.1 Flash (batch)","provider":"DeepSeek","family":null,"status":"active","variantType":"batch","modelVersion":"deepseek/deepseek-v4.1-flash-20260910","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"131072","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.112,"outputPrice":0.33599999999999997,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"inclusionai-ling-3-0-flash-vl","slug":"inclusionai-ling-3-0-flash-vl","canonicalId":"inclusionai-ling-3-0-flash-vl","name":"Ling 3.0 Flash VL","provider":"InclusionAI","family":null,"status":"active","variantType":"fast","modelVersion":"inclusionai/ling-3.0-flash-vl-20260910","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":6e-8,"completion":1.8e-7},"inputPrice":0.06,"outputPrice":0.18,"cachedInputPrice":null,"price":"$0.06","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":24.6,"coding":57,"agents":28.7,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-fp8","catalogSourceUrl":"/sources","sourceUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-fp8","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":97,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"inclusionai-ling-3-0-flash-vl","name":"Ling 3.0 Flash VL","provider":"InclusionAI","family":null,"status":"active","variantType":"fast","modelVersion":"inclusionai/ling-3.0-flash-vl-20260910","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"131072","maxOutputTokens":"32768","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.06,"outputPrice":0.18,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"inclusionai-ling-3-0-flash-vl-free","slug":"inclusionai-ling-3-0-flash-vl-free","canonicalId":"inclusionai-ling-3-0-flash-vl-free","name":"Ling 3.0 Flash VL (free)","provider":"InclusionAI","family":null,"status":"active","variantType":"free","modelVersion":"inclusionai/ling-3.0-flash-vl-20260910","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":24.6,"coding":57,"agents":28.7,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-fp8","catalogSourceUrl":"/sources","sourceUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-fp8","sourceUpdatedAt":{},"updated":"2026-09-23","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":98,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"inclusionai-ling-3-0-flash-vl-free","name":"Ling 3.0 Flash VL (free)","provider":"InclusionAI","family":null,"status":"active","variantType":"free","modelVersion":"inclusionai/ling-3.0-flash-vl-20260910","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"inception-mercury-2-5","slug":"inception-mercury-2-5","canonicalId":"inception-mercury-2-5","name":"Mercury 2.5","provider":"Inception","family":null,"status":"active","variantType":"base","modelVersion":"inception/mercury-2.5-20260908","modalities":["Text","Tools","Reasoning"],"context_length":"260000","context":"260000","contextWindow":"260000","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":4e-8,"completion":1.5e-7},"inputPrice":0.04,"outputPrice":0.15,"cachedInputPrice":null,"price":"$0.04","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":12.3,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":null,"catalogRank":99,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"inception-mercury-2-5","name":"Mercury 2.5","provider":"Inception","family":null,"status":"active","variantType":"base","modelVersion":"inception/mercury-2.5-20260908","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Tools","Reasoning"],"contextWindow":"260000","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.04,"outputPrice":0.15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"nex-agi-nex-n2-5-mini","slug":"nex-agi-nex-n2-5-mini","canonicalId":"nex-agi-nex-n2-5-mini","name":"Nex-N2.5-Mini","provider":"Nex AGI","family":null,"status":"active","variantType":"fast","modelVersion":"nex-agi/nex-n2.5-mini-20260908","modalities":["Text","Image","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":2.5e-8,"completion":1e-7},"inputPrice":0.024999999999999998,"outputPrice":0.09999999999999999,"cachedInputPrice":null,"price":"$0.02","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":100,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"nex-agi-nex-n2-5-mini","name":"Nex-N2.5-Mini","provider":"Nex AGI","family":null,"status":"active","variantType":"fast","modelVersion":"nex-agi/nex-n2.5-mini-20260908","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.024999999999999998,"outputPrice":0.09999999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"nex-agi-nex-n2-5-pro","slug":"nex-agi-nex-n2-5-pro","canonicalId":"nex-agi-nex-n2-5-pro","name":"Nex-N2.5-Pro","provider":"Nex AGI","family":null,"status":"active","variantType":"base","modelVersion":"nex-agi/nex-n2.5-pro-20260907","modalities":["Text","Image","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":7.5e-8,"completion":2.5e-7},"inputPrice":0.075,"outputPrice":0.25,"cachedInputPrice":null,"price":"$0.07","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":101,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"nex-agi-nex-n2-5-pro","name":"Nex-N2.5-Pro","provider":"Nex AGI","family":null,"status":"active","variantType":"base","modelVersion":"nex-agi/nex-n2.5-pro-20260907","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.075,"outputPrice":0.25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"inclusionai-ling-3-0-flash-sante","slug":"inclusionai-ling-3-0-flash-sante","canonicalId":"inclusionai-ling-3-0-flash-sante","name":"Ling 3.0 Flash Sante","provider":"InclusionAI","family":null,"status":"active","variantType":"fast","modelVersion":"inclusionai/ling-3.0-flash-sante-20260904","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":4.2e-8,"completion":1.232e-7},"inputPrice":0.041999999999999996,"outputPrice":0.12319999999999999,"cachedInputPrice":null,"price":"$0.04","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-fp8","catalogSourceUrl":"/sources","sourceUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-fp8","sourceUpdatedAt":{},"updated":"2026-10-13","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":null,"catalogRank":102,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"inclusionai-ling-3-0-flash-sante","name":"Ling 3.0 Flash Sante","provider":"InclusionAI","family":null,"status":"active","variantType":"fast","modelVersion":"inclusionai/ling-3.0-flash-sante-20260904","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.041999999999999996,"outputPrice":0.12319999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"inclusionai-ling-3-0-flash-sante-free","slug":"inclusionai-ling-3-0-flash-sante-free","canonicalId":"inclusionai-ling-3-0-flash-sante-free","name":"Ling 3.0 Flash Sante (free)","provider":"InclusionAI","family":null,"status":"active","variantType":"free","modelVersion":"inclusionai/ling-3.0-flash-sante-20260904","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-fp8","catalogSourceUrl":"/sources","sourceUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-fp8","sourceUpdatedAt":{},"updated":"2026-10-08","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":null,"catalogRank":103,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"inclusionai-ling-3-0-flash-sante-free","name":"Ling 3.0 Flash Sante (free)","provider":"InclusionAI","family":null,"status":"active","variantType":"free","modelVersion":"inclusionai/ling-3.0-flash-sante-20260904","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-6-astra-batch","slug":"openai-gpt-6-astra-batch","canonicalId":"openai-gpt-6-astra-batch","name":"GPT-6 Astra (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-6-astra-20260903","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000005,"completion":0.000025},"inputPrice":5,"outputPrice":25,"cachedInputPrice":null,"price":"$5.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":52.7,"coding":76.9,"agents":51,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-6-astra:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-6-astra:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":104,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-6-astra-batch","name":"GPT-6 Astra (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-6-astra-20260903","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":5,"outputPrice":25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-6-astra-pro","slug":"openai-gpt-6-astra-pro","canonicalId":"openai-gpt-6-astra-pro","name":"GPT-6 Astra Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-6-astra-pro-20260903","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00001,"completion":0.00005},"inputPrice":10,"outputPrice":50,"cachedInputPrice":null,"price":"$10.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-6-astra-pro","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-6-astra-pro","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":105,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-6-astra-pro","name":"GPT-6 Astra Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-6-astra-pro-20260903","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":10,"outputPrice":50,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-6-astra-pro-batch","slug":"openai-gpt-6-astra-pro-batch","canonicalId":"openai-gpt-6-astra-pro-batch","name":"GPT-6 Astra Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-6-astra-pro-20260903","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000005,"completion":0.000025},"inputPrice":5,"outputPrice":25,"cachedInputPrice":null,"price":"$5.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-6-astra-pro:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-6-astra-pro:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":106,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-6-astra-pro-batch","name":"GPT-6 Astra Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-6-astra-pro-20260903","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":5,"outputPrice":25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-8-max-0902","slug":"qwen-qwen3-8-max-0902","canonicalId":"qwen-qwen3-8-max-0902","name":"Qwen3.8 Max (0902)","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.8-max-20260902","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000006},"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":45.4,"coding":76.2,"agents":56,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":107,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-8-max-0902","name":"Qwen3.8 Max (0902)","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.8-max-20260902","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-8-flash","slug":"google-gemini-3-8-flash","canonicalId":"google-gemini-3-8-flash","name":"Gemini 3.8 Flash","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-3.8-flash-20260902","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":7.5e-7,"completion":0.00000375},"inputPrice":0.75,"outputPrice":3.75,"cachedInputPrice":null,"price":"$0.75","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":40.9,"coding":76.3,"agents":40.2,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":108,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-8-flash","name":"Gemini 3.8 Flash","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-3.8-flash-20260902","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.75,"outputPrice":3.75,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-8-flash-batch","slug":"google-gemini-3-8-flash-batch","canonicalId":"google-gemini-3-8-flash-batch","name":"Gemini 3.8 Flash (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-3.8-flash-20260902","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":3.75e-7,"completion":0.000001875},"inputPrice":0.375,"outputPrice":1.875,"cachedInputPrice":null,"price":"$0.38","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":40.9,"coding":76.3,"agents":40.2,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":109,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-8-flash-batch","name":"Gemini 3.8 Flash (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-3.8-flash-20260902","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.375,"outputPrice":1.875,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"meta-muse-spark-1-3","slug":"meta-muse-spark-1-3","canonicalId":"meta-muse-spark-1-3","name":"Muse Spark 1.3","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta/muse-spark-1.3-20260902","modalities":["Text","Image","Video","File","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":0.00000125,"completion":0.00000425},"inputPrice":1.25,"outputPrice":4.25,"cachedInputPrice":null,"price":"$1.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":48.1,"coding":75.8,"agents":55.5,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}},"officialUrl":"https://www.llama.com/models/","catalogSourceUrl":"https://ai.meta.com/","sourceUrl":"https://www.llama.com/models/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=meta.com&sz=64","catalogRank":110,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"meta-muse-spark-1-3","name":"Muse Spark 1.3","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta/muse-spark-1.3-20260902","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Video","File","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.25,"outputPrice":4.25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"meta-muse-spark-1-3-contributor","slug":"meta-muse-spark-1-3-contributor","canonicalId":"meta-muse-spark-1-3-contributor","name":"Muse Spark 1.3 Contributor","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta/muse-spark-1.3-contributor-20260902","modalities":["Text","Image","Video","File","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":2e-7},"inputPrice":0.09999999999999999,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}},"officialUrl":"https://www.llama.com/models/","catalogSourceUrl":"https://ai.meta.com/","sourceUrl":"https://www.llama.com/models/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=meta.com&sz=64","catalogRank":111,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"meta-muse-spark-1-3-contributor","name":"Muse Spark 1.3 Contributor","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta/muse-spark-1.3-contributor-20260902","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Video","File","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-fable-5-1-batch","slug":"anthropic-claude-fable-5-1-batch","canonicalId":"anthropic-claude-fable-5-1-batch","name":"Claude Fable 5.1 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-fable-5.1-20260831","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000005,"completion":0.000025},"inputPrice":5,"outputPrice":25,"cachedInputPrice":null,"price":"$5.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":53.4,"coding":81.6,"agents":57.9,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":112,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-fable-5-1-batch","name":"Claude Fable 5.1 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-fable-5.1-20260831","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":5,"outputPrice":25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"ibm-granite-granite-4-2-8b","slug":"ibm-granite-granite-4-2-8b","canonicalId":"ibm-granite-granite-4-2-8b","name":"Granite 4.2 8B","provider":"IBM","family":null,"status":"active","variantType":"base","modelVersion":"ibm-granite/granite-4.2-8b-20260831","modalities":["Text","Tools","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"pricing":{"prompt":6e-8,"completion":2.5e-7},"inputPrice":0.06,"outputPrice":0.25,"cachedInputPrice":null,"price":"$0.06","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":11.1,"coding":22.4,"agents":1.3,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ibm.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ibm.com/"},"pricing":{"name":"Provider source","url":"https://ibm.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ibm.com/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://ibm.com/","sourceUrl":"https://ibm.com/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=ibm.com&sz=64","catalogRank":113,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"ibm-granite-granite-4-2-8b","name":"Granite 4.2 8B","provider":"IBM","family":null,"status":"active","variantType":"base","modelVersion":"ibm-granite/granite-4.2-8b-20260831","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.06,"outputPrice":0.25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ibm.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ibm.com/"},"pricing":{"name":"Provider source","url":"https://ibm.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ibm.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"inception-mercury-2-5-preview","slug":"inception-mercury-2-5-preview","canonicalId":"inception-mercury-2-5-preview","name":"Mercury 2.5 Preview","provider":"Inception","family":null,"status":"active","variantType":"preview","modelVersion":"inception/mercury-2.5-preview-20260831","modalities":["Text","Tools","Reasoning"],"context_length":"260000","context":"260000","contextWindow":"260000","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":4e-8,"completion":1.5e-7},"inputPrice":0.04,"outputPrice":0.15,"cachedInputPrice":null,"price":"$0.04","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-09-08","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":null,"catalogRank":114,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"inception-mercury-2-5-preview","name":"Mercury 2.5 Preview","provider":"Inception","family":null,"status":"active","variantType":"preview","modelVersion":"inception/mercury-2.5-preview-20260831","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Tools","Reasoning"],"contextWindow":"260000","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.04,"outputPrice":0.15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"tencent-hy4-preview","slug":"tencent-hy4-preview","canonicalId":"tencent-hy4-preview","name":"Hy4 preview","provider":"Tencent","family":null,"status":"active","variantType":"preview","modelVersion":"tencent/hy4-preview-20260827","modalities":["Text","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"64000","apiAvailable":true,"pricing":{"prompt":8.34e-7,"completion":0.000002501},"inputPrice":0.834,"outputPrice":2.501,"cachedInputPrice":null,"price":"$0.83","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"pricing":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"metrics":{},"fields":{}},"officialUrl":"https://cloud.tencent.com/product/hunyuan","catalogSourceUrl":"https://hunyuan.tencent.com/","sourceUrl":"https://cloud.tencent.com/product/hunyuan","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=tencent.com&sz=64","catalogRank":115,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"tencent-hy4-preview","name":"Hy4 preview","provider":"Tencent","family":null,"status":"active","variantType":"preview","modelVersion":"tencent/hy4-preview-20260827","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"64000","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.834,"outputPrice":2.501,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"pricing":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"inclusionai-ling-3-0-flash-fin","slug":"inclusionai-ling-3-0-flash-fin","canonicalId":"inclusionai-ling-3-0-flash-fin","name":"Ling 3.0 Flash Fin","provider":"InclusionAI","family":null,"status":"active","variantType":"fast","modelVersion":"inclusionai/ling-3.0-flash-fin-20260827","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":4.2e-8,"completion":1.232e-7},"inputPrice":0.041999999999999996,"outputPrice":0.12319999999999999,"cachedInputPrice":null,"price":"$0.04","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":22.6,"coding":55.6,"agents":27.9,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-fp8","catalogSourceUrl":"/sources","sourceUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-fp8","sourceUpdatedAt":{},"updated":"2026-10-13","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":null,"catalogRank":116,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"inclusionai-ling-3-0-flash-fin","name":"Ling 3.0 Flash Fin","provider":"InclusionAI","family":null,"status":"active","variantType":"fast","modelVersion":"inclusionai/ling-3.0-flash-fin-20260827","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.041999999999999996,"outputPrice":0.12319999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"inclusionai-ling-3-0-flash-fin-free","slug":"inclusionai-ling-3-0-flash-fin-free","canonicalId":"inclusionai-ling-3-0-flash-fin-free","name":"Ling 3.0 Flash Fin (free)","provider":"InclusionAI","family":null,"status":"active","variantType":"free","modelVersion":"inclusionai/ling-3.0-flash-fin-20260827","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":22.6,"coding":55.6,"agents":27.9,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-fp8","catalogSourceUrl":"/sources","sourceUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-fp8","sourceUpdatedAt":{},"updated":"2026-09-28","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":null,"catalogRank":117,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"inclusionai-ling-3-0-flash-fin-free","name":"Ling 3.0 Flash Fin (free)","provider":"InclusionAI","family":null,"status":"active","variantType":"free","modelVersion":"inclusionai/ling-3.0-flash-fin-20260827","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-flash-latest","slug":"z-ai-glm-flash-latest","canonicalId":"z-ai-glm-flash-latest","name":"GLM Flash Latest","provider":"Z.ai","family":null,"status":"active","variantType":"fast","modelVersion":"~z-ai/glm-flash-latest","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":3.6e-8,"completion":9e-7},"inputPrice":0.036,"outputPrice":0.8999999999999999,"cachedInputPrice":null,"price":"$0.04","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":118,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-flash-latest","name":"GLM Flash Latest","provider":"Z.ai","family":null,"status":"active","variantType":"fast","modelVersion":"~z-ai/glm-flash-latest","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.036,"outputPrice":0.8999999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-8-flash","slug":"qwen-qwen3-8-flash","canonicalId":"qwen-qwen3-8-flash","name":"Qwen3.8 Flash","provider":"Qwen","family":null,"status":"active","variantType":"fast","modelVersion":"qwen/qwen3.8-flash-20260826","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":1.5e-7,"completion":4.6999999999999995e-7},"inputPrice":0.15,"outputPrice":0.47,"cachedInputPrice":null,"price":"$0.15","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":119,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-8-flash","name":"Qwen3.8 Flash","provider":"Qwen","family":null,"status":"active","variantType":"fast","modelVersion":"qwen/qwen3.8-flash-20260826","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"131072","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.15,"outputPrice":0.47,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-5-3-flash-batch","slug":"z-ai-glm-5-3-flash-batch","canonicalId":"z-ai-glm-5-3-flash-batch","name":"GLM 5.3 Flash (batch)","provider":"Z.ai","family":null,"status":"active","variantType":"batch","modelVersion":"z-ai/glm-5.3-flash-20260826","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":6e-8,"completion":2e-7},"inputPrice":0.06,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"price":"$0.06","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":41.8,"coding":71.5,"agents":50.9,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":120,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-5-3-flash-batch","name":"GLM 5.3 Flash (batch)","provider":"Z.ai","family":null,"status":"active","variantType":"batch","modelVersion":"z-ai/glm-5.3-flash-20260826","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"131072","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.06,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-v4-flash-vision-exp","slug":"deepseek-deepseek-v4-flash-vision-exp","canonicalId":"deepseek-deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","provider":"DeepSeek","family":null,"status":"active","variantType":"preview","modelVersion":"deepseek/deepseek-v4-flash-vision-exp-20260821","modalities":["Text","Image","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"262144","apiAvailable":true,"pricing":{"prompt":2.156e-7,"completion":6.468e-7},"inputPrice":0.21559999999999999,"outputPrice":0.6468,"cachedInputPrice":null,"price":"$0.22","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":34.8,"coding":65,"agents":47.5,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":121,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","provider":"DeepSeek","family":null,"status":"active","variantType":"preview","modelVersion":"deepseek/deepseek-v4-flash-vision-exp-20260821","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"262144","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.21559999999999999,"outputPrice":0.6468,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-v4-flash-vision-exp-batch","slug":"deepseek-deepseek-v4-flash-vision-exp-batch","canonicalId":"deepseek-deepseek-v4-flash-vision-exp-batch","name":"DeepSeek V4 Flash Vision Exp (batch)","provider":"DeepSeek","family":null,"status":"active","variantType":"batch","modelVersion":"deepseek/deepseek-v4-flash-vision-exp-20260821","modalities":["Text","Image","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":1.1e-7,"completion":3.3e-7},"inputPrice":0.11,"outputPrice":0.33,"cachedInputPrice":null,"price":"$0.11","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-09-22","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":122,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-v4-flash-vision-exp-batch","name":"DeepSeek V4 Flash Vision Exp (batch)","provider":"DeepSeek","family":null,"status":"active","variantType":"batch","modelVersion":"deepseek/deepseek-v4-flash-vision-exp-20260821","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.11,"outputPrice":0.33,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"meta-muse-spark-1-2-contributor","slug":"meta-muse-spark-1-2-contributor","canonicalId":"meta-muse-spark-1-2-contributor","name":"Muse Spark 1.2 Contributor","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta/muse-spark-1.2-contributor-20260805","modalities":["Text","Image","Video","File","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":2e-7},"inputPrice":0.09999999999999999,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}},"officialUrl":"https://www.llama.com/models/","catalogSourceUrl":"https://ai.meta.com/","sourceUrl":"https://www.llama.com/models/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=meta.com&sz=64","catalogRank":123,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"meta-muse-spark-1-2-contributor","name":"Muse Spark 1.2 Contributor","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta/muse-spark-1.2-contributor-20260805","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","File","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"stealth-ox-alpha","slug":"stealth-ox-alpha","canonicalId":"stealth-ox-alpha","name":"Ox Alpha","provider":"Stealth","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"/sources","catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-08-26","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":"Proprietary","providerIconUrl":null,"catalogRank":124,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"stealth-ox-alpha","name":"Ox Alpha","provider":"Stealth","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":null,"apiAvailable":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"tencent-hy-mt2-1-8b","slug":"tencent-hy-mt2-1-8b","canonicalId":"tencent-hy-mt2-1-8b","name":"Hy-MT2-1.8B","provider":"Tencent","family":null,"status":"active","variantType":"base","modelVersion":"tencent/hy-mt2-1.8b-20260521","modalities":["Text"],"context_length":"8192","context":"8192","contextWindow":"8192","maxOutputTokens":"4096","apiAvailable":true,"pricing":{"prompt":4.4e-8,"completion":1.77e-7},"inputPrice":0.044,"outputPrice":0.17700000000000002,"cachedInputPrice":null,"price":"$0.04","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"pricing":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"metrics":{},"fields":{}},"officialUrl":"https://cloud.tencent.com/product/hunyuan","catalogSourceUrl":"https://hunyuan.tencent.com/","sourceUrl":"https://cloud.tencent.com/product/hunyuan","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=tencent.com&sz=64","catalogRank":125,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"tencent-hy-mt2-1-8b","name":"Hy-MT2-1.8B","provider":"Tencent","family":null,"status":"active","variantType":"base","modelVersion":"tencent/hy-mt2-1.8b-20260521","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text"],"contextWindow":"8192","maxOutputTokens":"4096","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.044,"outputPrice":0.17700000000000002,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"pricing":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"tencent-hy-mt2-30b-a3b","slug":"tencent-hy-mt2-30b-a3b","canonicalId":"tencent-hy-mt2-30b-a3b","name":"Hy-MT2-30B-A3B","provider":"Tencent","family":null,"status":"active","variantType":"base","modelVersion":"tencent/hy-mt2-30b-a3b-20260521","modalities":["Text"],"context_length":"8192","context":"8192","contextWindow":"8192","maxOutputTokens":"4096","apiAvailable":true,"pricing":{"prompt":7.4e-8,"completion":2.95e-7},"inputPrice":0.074,"outputPrice":0.295,"cachedInputPrice":null,"price":"$0.07","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"pricing":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"metrics":{},"fields":{}},"officialUrl":"https://cloud.tencent.com/product/hunyuan","catalogSourceUrl":"https://hunyuan.tencent.com/","sourceUrl":"https://cloud.tencent.com/product/hunyuan","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=tencent.com&sz=64","catalogRank":126,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"tencent-hy-mt2-30b-a3b","name":"Hy-MT2-30B-A3B","provider":"Tencent","family":null,"status":"active","variantType":"base","modelVersion":"tencent/hy-mt2-30b-a3b-20260521","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text"],"contextWindow":"8192","maxOutputTokens":"4096","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.074,"outputPrice":0.295,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"pricing":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"tencent-hy-mt2-7b","slug":"tencent-hy-mt2-7b","canonicalId":"tencent-hy-mt2-7b","name":"Hy-MT2-7B","provider":"Tencent","family":null,"status":"active","variantType":"base","modelVersion":"tencent/hy-mt2-7b-20260521","modalities":["Text"],"context_length":"8192","context":"8192","contextWindow":"8192","maxOutputTokens":"4096","apiAvailable":true,"pricing":{"prompt":7.4e-8,"completion":2.95e-7},"inputPrice":0.074,"outputPrice":0.295,"cachedInputPrice":null,"price":"$0.07","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"pricing":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"metrics":{},"fields":{}},"officialUrl":"https://cloud.tencent.com/product/hunyuan","catalogSourceUrl":"https://hunyuan.tencent.com/","sourceUrl":"https://cloud.tencent.com/product/hunyuan","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=tencent.com&sz=64","catalogRank":127,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"tencent-hy-mt2-7b","name":"Hy-MT2-7B","provider":"Tencent","family":null,"status":"active","variantType":"base","modelVersion":"tencent/hy-mt2-7b-20260521","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text"],"contextWindow":"8192","maxOutputTokens":"4096","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.074,"outputPrice":0.295,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"pricing":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-latest","slug":"z-ai-glm-latest","canonicalId":"z-ai-glm-latest","name":"GLM Latest","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"~z-ai/glm-latest","modalities":["Text","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":6.3e-8,"completion":0.0000044},"inputPrice":0.063,"outputPrice":4.4,"cachedInputPrice":null,"price":"$0.06","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":128,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-latest","name":"GLM Latest","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"~z-ai/glm-latest","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.063,"outputPrice":4.4,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-5-3","slug":"z-ai-glm-5-3","canonicalId":"z-ai-glm-5-3","name":"GLM 5.3","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-5.3-20260816","modalities":["Text","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":7.9e-8,"completion":0.0000048},"inputPrice":0.079,"outputPrice":4.8,"cachedInputPrice":null,"price":"$0.08","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":44.8,"coding":74.8,"agents":53.1,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":129,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-5-3","name":"GLM 5.3","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-5.3-20260816","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.079,"outputPrice":4.8,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-5-3-batch","slug":"z-ai-glm-5-3-batch","canonicalId":"z-ai-glm-5-3-batch","name":"GLM 5.3 (batch)","provider":"Z.ai","family":null,"status":"active","variantType":"batch","modelVersion":"z-ai/glm-5.3-20260816","modalities":["Text","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":4.5e-7,"completion":0.000002},"inputPrice":0.44999999999999996,"outputPrice":2,"cachedInputPrice":null,"price":"$0.45","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":44.8,"coding":74.8,"agents":53.1,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":130,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-5-3-batch","name":"GLM 5.3 (batch)","provider":"Z.ai","family":null,"status":"active","variantType":"batch","modelVersion":"z-ai/glm-5.3-20260816","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"131072","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.44999999999999996,"outputPrice":2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"dots-studio-dots-3-note-preview-free","slug":"dots-studio-dots-3-note-preview-free","canonicalId":"dots-studio-dots-3-note-preview-free","name":"Dots3-Note Preview (free)","provider":"Dots Studio","family":null,"status":"active","variantType":"free","modelVersion":"dots-studio/dots-3-note-preview-20260813","modalities":["Text","Image","Tools","Reasoning"],"context_length":"512000","context":"512000","contextWindow":"512000","maxOutputTokens":"460800","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"https://huggingface.co/dots-studio/dots3-note-prev","catalogSourceUrl":"/sources","sourceUrl":"https://huggingface.co/dots-studio/dots3-note-prev","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":null,"catalogRank":131,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"dots-studio-dots-3-note-preview-free","name":"Dots3-Note Preview (free)","provider":"Dots Studio","family":null,"status":"active","variantType":"free","modelVersion":"dots-studio/dots-3-note-preview-20260813","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"512000","maxOutputTokens":"460800","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-8-27b","slug":"qwen-qwen3-8-27b","canonicalId":"qwen-qwen3-8-27b","name":"Qwen3.8 27B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.8-27b-20260814","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":4e-8,"completion":0.0000023},"inputPrice":0.04,"outputPrice":2.3,"cachedInputPrice":null,"price":"$0.04","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":33.7,"coding":68.1,"agents":45.8,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":132,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-8-27b","name":"Qwen3.8 27B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.8-27b-20260814","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.04,"outputPrice":2.3,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-8-27b-free","slug":"qwen-qwen3-8-27b-free","canonicalId":"qwen-qwen3-8-27b-free","name":"Qwen3.8 27B (free)","provider":"Qwen","family":null,"status":"active","variantType":"free","modelVersion":"qwen/qwen3.8-27b-20260814","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":33.7,"coding":68.1,"agents":45.8,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-05","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":133,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-8-27b-free","name":"Qwen3.8 27B (free)","provider":"Qwen","family":null,"status":"active","variantType":"free","modelVersion":"qwen/qwen3.8-27b-20260814","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-7-flash-batch","slug":"google-gemini-3-7-flash-batch","canonicalId":"google-gemini-3-7-flash-batch","name":"Gemini 3.7 Flash (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-3.7-flash-20260813","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":3.75e-7,"completion":0.000001875},"inputPrice":0.375,"outputPrice":1.875,"cachedInputPrice":null,"price":"$0.38","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":39.6,"coding":71.5,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":134,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-7-flash-batch","name":"Gemini 3.7 Flash (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-3.7-flash-20260813","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.375,"outputPrice":1.875,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"bytedance-seed-seed-2-1-turbo","slug":"bytedance-seed-seed-2-1-turbo","canonicalId":"bytedance-seed-seed-2-1-turbo","name":"Seed 2.1 Turbo","provider":"ByteDance Seed","family":null,"status":"active","variantType":"base","modelVersion":"bytedance-seed/seed-2-1-turbo-20260810","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":5e-7,"completion":0.0000025},"inputPrice":0.5,"outputPrice":2.5,"cachedInputPrice":null,"price":"$0.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"pricing":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"metrics":{},"fields":{}},"officialUrl":"https://seed.bytedance.com/en/seed2_1","catalogSourceUrl":"https://seed.bytedance.com/","sourceUrl":"https://seed.bytedance.com/en/seed2_1","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=seed.bytedance.com&sz=64","catalogRank":135,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"bytedance-seed-seed-2-1-turbo","name":"Seed 2.1 Turbo","provider":"ByteDance Seed","family":null,"status":"active","variantType":"base","modelVersion":"bytedance-seed/seed-2-1-turbo-20260810","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.5,"outputPrice":2.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"pricing":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"bytedance-seed-seed-2-0-code","slug":"bytedance-seed-seed-2-0-code","canonicalId":"bytedance-seed-seed-2-0-code","name":"Seed-2.0-Code","provider":"ByteDance Seed","family":null,"status":"active","variantType":"base","modelVersion":"bytedance-seed/seed-2.0-code-20260730","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":5e-7,"completion":0.000003},"inputPrice":0.5,"outputPrice":3,"cachedInputPrice":null,"price":"$0.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"pricing":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"metrics":{},"fields":{}},"officialUrl":"https://seed.bytedance.com/en/seed2_1","catalogSourceUrl":"https://seed.bytedance.com/","sourceUrl":"https://seed.bytedance.com/en/seed2_1","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=seed.bytedance.com&sz=64","catalogRank":136,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"bytedance-seed-seed-2-0-code","name":"Seed-2.0-Code","provider":"ByteDance Seed","family":null,"status":"active","variantType":"base","modelVersion":"bytedance-seed/seed-2.0-code-20260730","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.5,"outputPrice":3,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"pricing":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-v4-pro-0813","slug":"deepseek-deepseek-v4-pro-0813","canonicalId":"deepseek-deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"deepseek/deepseek-v4-pro-20260813","modalities":["Text","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"393216","apiAvailable":true,"pricing":{"prompt":0.00000132,"completion":0.00000396},"inputPrice":1.32,"outputPrice":3.9600000000000004,"cachedInputPrice":null,"price":"$1.32","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":36,"coding":68.8,"agents":41.3,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":137,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"deepseek/deepseek-v4-pro-20260813","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"393216","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.32,"outputPrice":3.9600000000000004,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-v4-pro-0813-batch","slug":"deepseek-deepseek-v4-pro-0813-batch","canonicalId":"deepseek-deepseek-v4-pro-0813-batch","name":"DeepSeek V4 Pro 0813 (batch)","provider":"DeepSeek","family":null,"status":"active","variantType":"batch","modelVersion":"deepseek/deepseek-v4-pro-20260813","modalities":["Text","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":6.6e-7,"completion":0.00000198},"inputPrice":0.66,"outputPrice":1.9800000000000002,"cachedInputPrice":null,"price":"$0.66","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":36,"coding":68.8,"agents":41.3,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-09-22","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":138,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-v4-pro-0813-batch","name":"DeepSeek V4 Pro 0813 (batch)","provider":"DeepSeek","family":null,"status":"active","variantType":"batch","modelVersion":"deepseek/deepseek-v4-pro-20260813","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.66,"outputPrice":1.9800000000000002,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-8-2-4t-a95b","slug":"qwen-qwen3-8-2-4t-a95b","canonicalId":"qwen-qwen3-8-2-4t-a95b","name":"Qwen3.8 2.4T A95B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.8-2.4t-a95b-20260812","modalities":["Text","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000006},"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":39.9,"coding":71.9,"agents":50.1,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":139,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-8-2-4t-a95b","name":"Qwen3.8 2.4T A95B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.8-2.4t-a95b-20260812","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"131072","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-8-2-4t-a95b-batch","slug":"qwen-qwen3-8-2-4t-a95b-batch","canonicalId":"qwen-qwen3-8-2-4t-a95b-batch","name":"Qwen3.8 2.4T A95B (batch)","provider":"Qwen","family":null,"status":"active","variantType":"batch","modelVersion":"qwen/qwen3.8-2.4t-a95b-20260812","modalities":["Text","Tools","Reasoning"],"context_length":"1010000","context":"1010000","contextWindow":"1010000","maxOutputTokens":"909000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000006},"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":39.9,"coding":71.9,"agents":50.1,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-09-21","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":140,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-8-2-4t-a95b-batch","name":"Qwen3.8 2.4T A95B (batch)","provider":"Qwen","family":null,"status":"active","variantType":"batch","modelVersion":"qwen/qwen3.8-2.4t-a95b-20260812","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1010000","maxOutputTokens":"909000","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"x-ai-grok-4-6","slug":"x-ai-grok-4-6","canonicalId":"x-ai-grok-4-6","name":"Grok 4.6","provider":"xAI","family":null,"status":"active","variantType":"base","modelVersion":"x-ai/grok-4.6-20260810","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"500000","context":"500000","contextWindow":"500000","maxOutputTokens":"450000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000006},"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":44.3,"coding":76.8,"agents":53,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://x.ai/"},"pricing":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://x.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.x.ai/docs/models","catalogSourceUrl":"https://x.ai/","sourceUrl":"https://docs.x.ai/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=x.ai&sz=64","catalogRank":141,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"x-ai-grok-4-6","name":"Grok 4.6","provider":"xAI","family":null,"status":"active","variantType":"base","modelVersion":"x-ai/grok-4.6-20260810","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"500000","maxOutputTokens":"450000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://x.ai/"},"pricing":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://x.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"liquid-lfm-2-5-2-6b-free","slug":"liquid-lfm-2-5-2-6b-free","canonicalId":"liquid-lfm-2-5-2-6b-free","name":"LFM2.5-2.6B (free)","provider":"Liquid AI","family":null,"status":"active","variantType":"free","modelVersion":"liquid/lfm-2.5-2.6b-20260811","modalities":["Text","Tools","Reasoning"],"context_length":"65536","context":"65536","contextWindow":"65536","maxOutputTokens":"8192","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":8.4,"coding":7.7,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"https://www.liquid.ai/liquid-foundation-models","catalogSourceUrl":"/sources","sourceUrl":"https://www.liquid.ai/liquid-foundation-models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":142,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"liquid-lfm-2-5-2-6b-free","name":"LFM2.5-2.6B (free)","provider":"Liquid AI","family":null,"status":"active","variantType":"free","modelVersion":"liquid/lfm-2.5-2.6b-20260811","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"65536","maxOutputTokens":"8192","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"nvidia-nemotron-3-5-lightning","slug":"nvidia-nemotron-3-5-lightning","canonicalId":"nvidia-nemotron-3-5-lightning","name":"Nemotron 3.5 Lightning","provider":"NVIDIA","family":null,"status":"active","variantType":"base","modelVersion":"nvidia/nemotron-3.5-lightning-20260807","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":7e-8,"completion":2e-7},"inputPrice":0.07,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"price":"$0.07","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":12.9,"coding":26.8,"agents":3.5,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}},"officialUrl":"https://build.nvidia.com/explore/discover","catalogSourceUrl":"https://nvidia.com/","sourceUrl":"https://build.nvidia.com/explore/discover","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=nvidia.com&sz=64","catalogRank":143,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"nvidia-nemotron-3-5-lightning","name":"Nemotron 3.5 Lightning","provider":"NVIDIA","family":null,"status":"active","variantType":"base","modelVersion":"nvidia/nemotron-3.5-lightning-20260807","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.07,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"nvidia-nemotron-3-5-lightning-free","slug":"nvidia-nemotron-3-5-lightning-free","canonicalId":"nvidia-nemotron-3-5-lightning-free","name":"Nemotron 3.5 Lightning (free)","provider":"NVIDIA","family":null,"status":"active","variantType":"free","modelVersion":"nvidia/nemotron-3.5-lightning-20260807","modalities":["Text","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":12.9,"coding":26.8,"agents":3.5,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}},"officialUrl":"https://build.nvidia.com/explore/discover","catalogSourceUrl":"https://nvidia.com/","sourceUrl":"https://build.nvidia.com/explore/discover","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=nvidia.com&sz=64","catalogRank":144,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"nvidia-nemotron-3-5-lightning-free","name":"Nemotron 3.5 Lightning (free)","provider":"NVIDIA","family":null,"status":"active","variantType":"free","modelVersion":"nvidia/nemotron-3.5-lightning-20260807","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"65536","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"sakana-sakana-namazu","slug":"sakana-sakana-namazu","canonicalId":"sakana-sakana-namazu","name":"Sakana Namazu","provider":"Sakana","family":null,"status":"active","variantType":"base","modelVersion":"sakana/namazu-20260811","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":9.499999999999999e-7,"completion":0.000004},"inputPrice":0.95,"outputPrice":4,"cachedInputPrice":null,"price":"$0.95","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://sakana.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://sakana.ai/"},"pricing":{"name":"Provider source","url":"https://sakana.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://sakana.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://sakana.ai/namazu-api/","catalogSourceUrl":"https://sakana.ai/","sourceUrl":"https://sakana.ai/namazu-api/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=sakana.ai&sz=64","catalogRank":145,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"sakana-sakana-namazu","name":"Sakana Namazu","provider":"Sakana","family":null,"status":"active","variantType":"base","modelVersion":"sakana/namazu-20260811","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.95,"outputPrice":4,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://sakana.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://sakana.ai/"},"pricing":{"name":"Provider source","url":"https://sakana.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://sakana.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"upstage-solar-pro4","slug":"upstage-solar-pro4","canonicalId":"upstage-solar-pro4","name":"Solar Pro 4","provider":"Upstage","family":null,"status":"active","variantType":"base","modelVersion":"upstage/solar-pro4-20260810","modalities":["Text","Tools","Reasoning"],"context_length":"524288","context":"524288","contextWindow":"524288","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":9e-8,"completion":3.6e-7},"inputPrice":0.09,"outputPrice":0.36,"cachedInputPrice":null,"price":"$0.09","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":28.2,"coding":52.7,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://upstage.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://upstage.ai/"},"pricing":{"name":"Provider source","url":"https://upstage.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://upstage.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.upstage.ai/docs/apis/chat","catalogSourceUrl":"https://upstage.ai/","sourceUrl":"https://developers.upstage.ai/docs/apis/chat","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=upstage.ai&sz=64","catalogRank":146,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"upstage-solar-pro4","name":"Solar Pro 4","provider":"Upstage","family":null,"status":"active","variantType":"base","modelVersion":"upstage/solar-pro4-20260810","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Tools","Reasoning"],"contextWindow":"524288","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.09,"outputPrice":0.36,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://upstage.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://upstage.ai/"},"pricing":{"name":"Provider source","url":"https://upstage.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://upstage.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"meta-muse-glimmer-30b","slug":"meta-muse-glimmer-30b","canonicalId":"meta-muse-glimmer-30b","name":"Muse Glimmer 30B","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta/muse-glimmer-30b-20260810","modalities":["Text","Image","Tools","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":3e-7,"completion":0.0000012},"inputPrice":0.3,"outputPrice":1.2,"cachedInputPrice":null,"price":"$0.30","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":17.5,"coding":49,"agents":8.5,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}},"officialUrl":"https://www.llama.com/models/","catalogSourceUrl":"https://ai.meta.com/","sourceUrl":"https://www.llama.com/models/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=meta.com&sz=64","catalogRank":147,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"meta-muse-glimmer-30b","name":"Muse Glimmer 30B","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta/muse-glimmer-30b-20260810","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.3,"outputPrice":1.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"meta-muse-glimmer-30b-batch","slug":"meta-muse-glimmer-30b-batch","canonicalId":"meta-muse-glimmer-30b-batch","name":"Muse Glimmer 30B (batch)","provider":"Meta","family":null,"status":"active","variantType":"batch","modelVersion":"meta/muse-glimmer-30b-20260810","modalities":["Text","Image","Tools","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"pricing":{"prompt":1.75e-7,"completion":7.5e-7},"inputPrice":0.175,"outputPrice":0.75,"cachedInputPrice":null,"price":"$0.17","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}},"officialUrl":"https://www.llama.com/models/","catalogSourceUrl":"https://ai.meta.com/","sourceUrl":"https://www.llama.com/models/","sourceUpdatedAt":{},"updated":"2026-09-22","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=meta.com&sz=64","catalogRank":148,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"meta-muse-glimmer-30b-batch","name":"Muse Glimmer 30B (batch)","provider":"Meta","family":null,"status":"active","variantType":"batch","modelVersion":"meta/muse-glimmer-30b-20260810","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.175,"outputPrice":0.75,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"meta-muse-spark-1-2","slug":"meta-muse-spark-1-2","canonicalId":"meta-muse-spark-1-2","name":"Muse Spark 1.2","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta/muse-spark-1.2-20260805","modalities":["Text","Image","Video","File","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":0.00000125,"completion":0.00000425},"inputPrice":1.25,"outputPrice":4.25,"cachedInputPrice":null,"price":"$1.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":39.6,"coding":72.2,"agents":43.2,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}},"officialUrl":"https://www.llama.com/models/","catalogSourceUrl":"https://ai.meta.com/","sourceUrl":"https://www.llama.com/models/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=meta.com&sz=64","catalogRank":149,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"meta-muse-spark-1-2","name":"Muse Spark 1.2","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta/muse-spark-1.2-20260805","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","File","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.25,"outputPrice":4.25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-8-max","slug":"qwen-qwen3-8-max","canonicalId":"qwen-qwen3-8-max","name":"Qwen3.8 Max","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.8-max-20260803","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000006},"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":53.4,"coding":68.9,"agents":49.9,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-09-05","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":150,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-8-max","name":"Qwen3.8 Max","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.8-max-20260803","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-v4-flash-latest","slug":"deepseek-deepseek-v4-flash-latest","canonicalId":"deepseek-deepseek-v4-flash-latest","name":"DeepSeek V4 Flash Latest","provider":"DeepSeek","family":null,"status":"active","variantType":"fast","modelVersion":"~deepseek/deepseek-v4-flash-latest","modalities":["Text","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":1.44e-8,"completion":5.76e-7},"inputPrice":0.0144,"outputPrice":0.576,"cachedInputPrice":null,"price":"$0.01","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":151,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-v4-flash-latest","name":"DeepSeek V4 Flash Latest","provider":"DeepSeek","family":null,"status":"active","variantType":"fast","modelVersion":"~deepseek/deepseek-v4-flash-latest","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.0144,"outputPrice":0.576,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-v4-flash-0731","slug":"deepseek-deepseek-v4-flash-0731","canonicalId":"deepseek-deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","provider":"DeepSeek","family":null,"status":"active","variantType":"fast","modelVersion":"deepseek/deepseek-v4-flash-20260731","modalities":["Text","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":1.6e-8,"completion":6.4e-7},"inputPrice":0.016,"outputPrice":0.64,"cachedInputPrice":null,"price":"$0.02","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":34.3,"coding":69.1,"agents":41,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":152,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","provider":"DeepSeek","family":null,"status":"active","variantType":"fast","modelVersion":"deepseek/deepseek-v4-flash-20260731","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.016,"outputPrice":0.64,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-v4-flash-0731-batch","slug":"deepseek-deepseek-v4-flash-0731-batch","canonicalId":"deepseek-deepseek-v4-flash-0731-batch","name":"DeepSeek V4 Flash 0731 (batch)","provider":"DeepSeek","family":null,"status":"active","variantType":"batch","modelVersion":"deepseek/deepseek-v4-flash-20260731","modalities":["Text","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":1.1e-7,"completion":3.3e-7},"inputPrice":0.11,"outputPrice":0.33,"cachedInputPrice":null,"price":"$0.11","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":34.3,"coding":69.1,"agents":41,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-09-22","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":153,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-v4-flash-0731-batch","name":"DeepSeek V4 Flash 0731 (batch)","provider":"DeepSeek","family":null,"status":"active","variantType":"batch","modelVersion":"deepseek/deepseek-v4-flash-20260731","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.11,"outputPrice":0.33,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-v4-flash-0731-free","slug":"deepseek-deepseek-v4-flash-0731-free","canonicalId":"deepseek-deepseek-v4-flash-0731-free","name":"DeepSeek V4 Flash 0731 (free)","provider":"DeepSeek","family":null,"status":"active","variantType":"free","modelVersion":"deepseek/deepseek-v4-flash-20260731","modalities":["Text","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"393216","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":34.3,"coding":69.1,"agents":41,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-09-20","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":154,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-v4-flash-0731-free","name":"DeepSeek V4 Flash 0731 (free)","provider":"DeepSeek","family":null,"status":"active","variantType":"free","modelVersion":"deepseek/deepseek-v4-flash-20260731","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"393216","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"thinkingmachines-inkling-small","slug":"thinkingmachines-inkling-small","canonicalId":"thinkingmachines-inkling-small","name":"Inkling Small","provider":"Thinking Machines","family":null,"status":"active","variantType":"base","modelVersion":"thinkingmachines/inkling-small-20260730","modalities":["Text","Image","Audio","Tools","Reasoning"],"context_length":"524288","context":"524288","contextWindow":"524288","maxOutputTokens":"262144","apiAvailable":true,"pricing":{"prompt":4.5e-7,"completion":0.0000012},"inputPrice":0.44999999999999996,"outputPrice":1.2,"cachedInputPrice":null,"price":"$0.45","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":25.7,"coding":52.9,"agents":23.5,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"https://thinkingmachines.ai/model-card/inkling-small/","catalogSourceUrl":"/sources","sourceUrl":"https://thinkingmachines.ai/model-card/inkling-small/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":155,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"thinkingmachines-inkling-small","name":"Inkling Small","provider":"Thinking Machines","family":null,"status":"active","variantType":"base","modelVersion":"thinkingmachines/inkling-small-20260730","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Audio","Tools","Reasoning"],"contextWindow":"524288","maxOutputTokens":"262144","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.44999999999999996,"outputPrice":1.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"thinkingmachines-inkling-small-batch","slug":"thinkingmachines-inkling-small-batch","canonicalId":"thinkingmachines-inkling-small-batch","name":"Inkling Small (batch)","provider":"Thinking Machines","family":null,"status":"active","variantType":"batch","modelVersion":"thinkingmachines/inkling-small-20260730","modalities":["Text","Image","Audio","Tools","Reasoning"],"context_length":"524288","context":"524288","contextWindow":"524288","maxOutputTokens":"471859","apiAvailable":true,"pricing":{"prompt":5e-7,"completion":0.0000012},"inputPrice":0.5,"outputPrice":1.2,"cachedInputPrice":null,"price":"$0.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":26.1,"coding":52.9,"agents":25,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"https://thinkingmachines.ai/model-card/inkling-small/","catalogSourceUrl":"/sources","sourceUrl":"https://thinkingmachines.ai/model-card/inkling-small/","sourceUpdatedAt":{},"updated":"2026-09-15","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":156,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"thinkingmachines-inkling-small-batch","name":"Inkling Small (batch)","provider":"Thinking Machines","family":null,"status":"active","variantType":"batch","modelVersion":"thinkingmachines/inkling-small-20260730","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Audio","Tools","Reasoning"],"contextWindow":"524288","maxOutputTokens":"471859","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.5,"outputPrice":1.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"thinkingmachines-inkling-small-free","slug":"thinkingmachines-inkling-small-free","canonicalId":"thinkingmachines-inkling-small-free","name":"Inkling Small (free)","provider":"Thinking Machines","family":null,"status":"active","variantType":"free","modelVersion":"thinkingmachines/inkling-small-20260730","modalities":["Text","Image","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"262144","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":25.7,"coding":52.9,"agents":23.5,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"https://thinkingmachines.ai/model-card/inkling-small/","catalogSourceUrl":"/sources","sourceUrl":"https://thinkingmachines.ai/model-card/inkling-small/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":157,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"thinkingmachines-inkling-small-free","name":"Inkling Small (free)","provider":"Thinking Machines","family":null,"status":"active","variantType":"free","modelVersion":"thinkingmachines/inkling-small-20260730","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"262144","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-7-flash","slug":"qwen-qwen3-7-flash","canonicalId":"qwen-qwen3-7-flash","name":"Qwen3.7 Flash","provider":"Qwen","family":null,"status":"active","variantType":"fast","modelVersion":"qwen/qwen3.7-flash-20260727","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":3e-8,"completion":1.3e-7},"inputPrice":0.03,"outputPrice":0.13,"cachedInputPrice":null,"price":"$0.03","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":158,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-7-flash","name":"Qwen3.7 Flash","provider":"Qwen","family":null,"status":"active","variantType":"fast","modelVersion":"qwen/qwen3.7-flash-20260727","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.03,"outputPrice":0.13,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-opus-5-batch","slug":"anthropic-claude-opus-5-batch","canonicalId":"anthropic-claude-opus-5-batch","name":"Claude Opus 5 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-opus-5-20260723","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.0000125},"inputPrice":2.5,"outputPrice":12.5,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":50.8,"coding":78,"agents":56.5,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":159,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-opus-5-batch","name":"Claude Opus 5 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-opus-5-20260723","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2.5,"outputPrice":12.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-opus-5-fast","slug":"anthropic-claude-opus-5-fast","canonicalId":"anthropic-claude-opus-5-fast","name":"Claude Opus 5 (Fast)","provider":"Anthropic","family":null,"status":"active","variantType":"fast","modelVersion":"anthropic/claude-opus-5-fast-20260723","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00001,"completion":0.00005},"inputPrice":10,"outputPrice":50,"cachedInputPrice":null,"price":"$10.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-09-01","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":160,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-opus-5-fast","name":"Claude Opus 5 (Fast)","provider":"Anthropic","family":null,"status":"active","variantType":"fast","modelVersion":"anthropic/claude-opus-5-fast-20260723","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":10,"outputPrice":50,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"inclusionai-ling-3-0-flash","slug":"inclusionai-ling-3-0-flash","canonicalId":"inclusionai-ling-3-0-flash","name":"Ling 3.0 Flash","provider":"InclusionAI","family":null,"status":"active","variantType":"fast","modelVersion":"inclusionai/ling-3.0-flash-20260723","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":2.1e-8,"completion":6.3e-8},"inputPrice":0.020999999999999998,"outputPrice":0.063,"cachedInputPrice":null,"price":"$0.02","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":20.1,"coding":50.6,"agents":19.3,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-fp8","catalogSourceUrl":"/sources","sourceUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-fp8","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":161,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"inclusionai-ling-3-0-flash","name":"Ling 3.0 Flash","provider":"InclusionAI","family":null,"status":"active","variantType":"fast","modelVersion":"inclusionai/ling-3.0-flash-20260723","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.020999999999999998,"outputPrice":0.063,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-5-flash-lite","slug":"google-gemini-3-5-flash-lite","canonicalId":"google-gemini-3-5-flash-lite","name":"Gemini 3.5 Flash Lite","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-3.5-flash-lite-20260721","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":3e-7,"completion":0.0000025},"inputPrice":0.3,"outputPrice":2.5,"cachedInputPrice":null,"price":"$0.30","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":22.2,"coding":49.3,"agents":14.3,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":162,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-5-flash-lite","name":"Gemini 3.5 Flash Lite","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-3.5-flash-lite-20260721","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.3,"outputPrice":2.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-5-flash-lite-batch","slug":"google-gemini-3-5-flash-lite-batch","canonicalId":"google-gemini-3-5-flash-lite-batch","name":"Gemini 3.5 Flash Lite (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-3.5-flash-lite-20260721","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":1.5e-7,"completion":0.00000125},"inputPrice":0.15,"outputPrice":1.25,"cachedInputPrice":null,"price":"$0.15","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":22.2,"coding":49.3,"agents":14.3,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":163,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-5-flash-lite-batch","name":"Gemini 3.5 Flash Lite (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-3.5-flash-lite-20260721","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.15,"outputPrice":1.25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-6-flash","slug":"google-gemini-3-6-flash","canonicalId":"google-gemini-3-6-flash","name":"Gemini 3.6 Flash","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-3.6-flash-20260721","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":7.5e-7,"completion":0.00000375},"inputPrice":0.75,"outputPrice":3.75,"cachedInputPrice":null,"price":"$0.75","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":34,"coding":69.2,"agents":29,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":164,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-6-flash","name":"Gemini 3.6 Flash","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-3.6-flash-20260721","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.75,"outputPrice":3.75,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-6-flash-batch","slug":"google-gemini-3-6-flash-batch","canonicalId":"google-gemini-3-6-flash-batch","name":"Gemini 3.6 Flash (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-3.6-flash-20260721","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":3.75e-7,"completion":0.000001875},"inputPrice":0.375,"outputPrice":1.875,"cachedInputPrice":null,"price":"$0.38","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":34,"coding":69.2,"agents":29,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":165,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-6-flash-batch","name":"Gemini 3.6 Flash (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-3.6-flash-20260721","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.375,"outputPrice":1.875,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"poolside-laguna-s-2-1","slug":"poolside-laguna-s-2-1","canonicalId":"poolside-laguna-s-2-1","name":"Laguna S 2.1","provider":"Poolside","family":null,"status":"active","variantType":"base","modelVersion":"poolside/laguna-s-2.1-20260720","modalities":["Text","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":9e-8,"completion":1.8e-7},"inputPrice":0.09,"outputPrice":0.18,"cachedInputPrice":null,"price":"$0.09","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://poolside.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://poolside.ai/"},"pricing":{"name":"Provider source","url":"https://poolside.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://poolside.ai/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://poolside.ai/","sourceUrl":"https://poolside.ai/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=poolside.ai&sz=64","catalogRank":166,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"poolside-laguna-s-2-1","name":"Laguna S 2.1","provider":"Poolside","family":null,"status":"active","variantType":"base","modelVersion":"poolside/laguna-s-2.1-20260720","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"131072","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.09,"outputPrice":0.18,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://poolside.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://poolside.ai/"},"pricing":{"name":"Provider source","url":"https://poolside.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://poolside.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"poolside-laguna-s-2-1-free","slug":"poolside-laguna-s-2-1-free","canonicalId":"poolside-laguna-s-2-1-free","name":"Laguna S 2.1 (free)","provider":"Poolside","family":null,"status":"active","variantType":"free","modelVersion":"poolside/laguna-s-2.1-20260720","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://poolside.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://poolside.ai/"},"pricing":{"name":"Provider source","url":"https://poolside.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://poolside.ai/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://poolside.ai/","sourceUrl":"https://poolside.ai/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=poolside.ai&sz=64","catalogRank":167,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"poolside-laguna-s-2-1-free","name":"Laguna S 2.1 (free)","provider":"Poolside","family":null,"status":"active","variantType":"free","modelVersion":"poolside/laguna-s-2.1-20260720","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://poolside.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://poolside.ai/"},"pricing":{"name":"Provider source","url":"https://poolside.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://poolside.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"meituan-longcat-2-0","slug":"meituan-longcat-2-0","canonicalId":"meituan-longcat-2-0","name":"LongCat 2.0","provider":"Meituan","family":null,"status":"active","variantType":"base","modelVersion":"meituan/longcat-2.0-20260720","modalities":["Text","Tools","Reasoning"],"context_length":"1048756","context":"1048756","contextWindow":"1048756","maxOutputTokens":"262144","apiAvailable":true,"pricing":{"prompt":3e-7,"completion":0.0000012},"inputPrice":0.3,"outputPrice":1.2,"cachedInputPrice":null,"price":"$0.30","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":19.1,"coding":45.3,"agents":14,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://meituan.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://meituan.com/"},"pricing":{"name":"Provider source","url":"https://meituan.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://meituan.com/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://meituan.com/","sourceUrl":"https://meituan.com/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=meituan.com&sz=64","catalogRank":168,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"meituan-longcat-2-0","name":"LongCat 2.0","provider":"Meituan","family":null,"status":"active","variantType":"base","modelVersion":"meituan/longcat-2.0-20260720","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1048756","maxOutputTokens":"262144","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.3,"outputPrice":1.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://meituan.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://meituan.com/"},"pricing":{"name":"Provider source","url":"https://meituan.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://meituan.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openrouter-auto-beta","slug":"openrouter-auto-beta","canonicalId":"openrouter-auto-beta","name":"Auto Router (Beta)","provider":"OpenRouter","family":null,"status":"active","variantType":"router","modelVersion":"openrouter/auto-beta","modalities":["Text","Image","Audio","File","Video","Tools"],"context_length":"2000000","context":"2000000","contextWindow":"2000000","maxOutputTokens":null,"apiAvailable":true,"pricing":{"prompt":null,"completion":null},"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"price":"N/A","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":null,"catalogRank":169,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openrouter-auto-beta","name":"Auto Router (Beta)","provider":"OpenRouter","family":null,"status":"active","variantType":"router","modelVersion":"openrouter/auto-beta","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Audio","File","Video","Tools"],"contextWindow":"2000000","maxOutputTokens":null,"apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"thinkingmachines-inkling","slug":"thinkingmachines-inkling","canonicalId":"thinkingmachines-inkling","name":"Inkling","provider":"Thinking Machines","family":null,"status":"active","variantType":"base","modelVersion":"thinkingmachines/inkling-20260715","modalities":["Text","Image","Audio","Tools","Reasoning"],"context_length":"524288","context":"524288","contextWindow":"524288","maxOutputTokens":"471859","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.00000405},"inputPrice":1,"outputPrice":4.05,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":25,"coding":52.1,"agents":22.5,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"https://thinkingmachines.ai/model-card/inkling-small/","catalogSourceUrl":"/sources","sourceUrl":"https://thinkingmachines.ai/model-card/inkling-small/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":170,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"thinkingmachines-inkling","name":"Inkling","provider":"Thinking Machines","family":null,"status":"active","variantType":"base","modelVersion":"thinkingmachines/inkling-20260715","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Audio","Tools","Reasoning"],"contextWindow":"524288","maxOutputTokens":"471859","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":4.05,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"thinkingmachines-inkling-batch","slug":"thinkingmachines-inkling-batch","canonicalId":"thinkingmachines-inkling-batch","name":"Inkling (batch)","provider":"Thinking Machines","family":null,"status":"active","variantType":"batch","modelVersion":"thinkingmachines/inkling-20260715","modalities":["Text","Image","Audio","Tools","Reasoning"],"context_length":"524288","context":"524288","contextWindow":"524288","maxOutputTokens":"471859","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.00000405},"inputPrice":1,"outputPrice":4.05,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":25,"coding":52.1,"agents":22.5,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"https://thinkingmachines.ai/model-card/inkling-small/","catalogSourceUrl":"/sources","sourceUrl":"https://thinkingmachines.ai/model-card/inkling-small/","sourceUpdatedAt":{},"updated":"2026-09-21","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":171,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"thinkingmachines-inkling-batch","name":"Inkling (batch)","provider":"Thinking Machines","family":null,"status":"active","variantType":"batch","modelVersion":"thinkingmachines/inkling-20260715","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Audio","Tools","Reasoning"],"contextWindow":"524288","maxOutputTokens":"471859","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":4.05,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"thinkingmachines-inkling-free","slug":"thinkingmachines-inkling-free","canonicalId":"thinkingmachines-inkling-free","name":"Inkling (free)","provider":"Thinking Machines","family":null,"status":"active","variantType":"free","modelVersion":"thinkingmachines/inkling-20260715","modalities":["Text","Image","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"262144","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":25,"coding":52.1,"agents":22.5,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"https://thinkingmachines.ai/model-card/inkling-small/","catalogSourceUrl":"/sources","sourceUrl":"https://thinkingmachines.ai/model-card/inkling-small/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":172,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"thinkingmachines-inkling-free","name":"Inkling (free)","provider":"Thinking Machines","family":null,"status":"active","variantType":"free","modelVersion":"thinkingmachines/inkling-20260715","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"262144","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"meta-muse-spark-1-1","slug":"meta-muse-spark-1-1","canonicalId":"meta-muse-spark-1-1","name":"Muse Spark 1.1","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta/muse-spark-1.1-20260709","modalities":["Text","Image","Video","File","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":0.00000125,"completion":0.00000425},"inputPrice":1.25,"outputPrice":4.25,"cachedInputPrice":null,"price":"$1.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":33.7,"coding":71.3,"agents":25.8,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}},"officialUrl":"https://www.llama.com/models/","catalogSourceUrl":"https://ai.meta.com/","sourceUrl":"https://www.llama.com/models/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=meta.com&sz=64","catalogRank":173,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"meta-muse-spark-1-1","name":"Muse Spark 1.1","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta/muse-spark-1.1-20260709","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","File","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.25,"outputPrice":4.25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"moonshotai-kimi-k3-batch","slug":"moonshotai-kimi-k3-batch","canonicalId":"moonshotai-kimi-k3-batch","name":"Kimi K3 (batch)","provider":"Moonshot AI","family":null,"status":"active","variantType":"batch","modelVersion":"moonshotai/kimi-k3-20260715","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":0.00000228,"completion":0.0000114},"inputPrice":2.2800000000000002,"outputPrice":11.399999999999999,"cachedInputPrice":null,"price":"$2.28","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":43.6,"coding":76.2,"agents":50,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://platform.moonshot.ai/docs/guide/models","catalogSourceUrl":"https://moonshot.ai/","sourceUrl":"https://platform.moonshot.ai/docs/guide/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=moonshot.ai&sz=64","catalogRank":174,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"moonshotai-kimi-k3-batch","name":"Kimi K3 (batch)","provider":"Moonshot AI","family":null,"status":"active","variantType":"batch","modelVersion":"moonshotai/kimi-k3-20260715","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2.2800000000000002,"outputPrice":11.399999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"kwaipilot-kat-coder-air-v2-5","slug":"kwaipilot-kat-coder-air-v2-5","canonicalId":"kwaipilot-kat-coder-air-v2-5","name":"KAT-Coder-Air V2.5","provider":"KwaiPilot","family":null,"status":"active","variantType":"base","modelVersion":"kwaipilot/kat-coder-air-v2.5-20260710","modalities":["Text","Tools"],"context_length":"256000","context":"256000","contextWindow":"256000","maxOutputTokens":"80000","apiAvailable":true,"pricing":{"prompt":1.5e-7,"completion":6e-7},"inputPrice":0.15,"outputPrice":0.6,"cachedInputPrice":null,"price":"$0.15","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-08-31","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":null,"catalogRank":175,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"kwaipilot-kat-coder-air-v2-5","name":"KAT-Coder-Air V2.5","provider":"KwaiPilot","family":null,"status":"active","variantType":"base","modelVersion":"kwaipilot/kat-coder-air-v2.5-20260710","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Tools"],"contextWindow":"256000","maxOutputTokens":"80000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.15,"outputPrice":0.6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"kwaipilot-kat-coder-pro-v2-5","slug":"kwaipilot-kat-coder-pro-v2-5","canonicalId":"kwaipilot-kat-coder-pro-v2-5","name":"KAT-Coder-Pro V2.5","provider":"KwaiPilot","family":null,"status":"active","variantType":"base","modelVersion":"kwaipilot/kat-coder-pro-v2.5-20260710","modalities":["Text","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":7.4e-7,"completion":0.00000296},"inputPrice":0.74,"outputPrice":2.96,"cachedInputPrice":null,"price":"$0.74","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-07","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":null,"catalogRank":176,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"kwaipilot-kat-coder-pro-v2-5","name":"KAT-Coder-Pro V2.5","provider":"KwaiPilot","family":null,"status":"active","variantType":"base","modelVersion":"kwaipilot/kat-coder-pro-v2.5-20260710","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Tools"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.74,"outputPrice":2.96,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-6-luna-batch","slug":"openai-gpt-5-6-luna-batch","canonicalId":"openai-gpt-5-6-luna-batch","name":"GPT-5.6 Luna (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.6-luna-20260709","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":6e-7},"inputPrice":0.09999999999999999,"outputPrice":0.6,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":37.3,"coding":71.4,"agents":42.1,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-luna:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-luna:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":177,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-6-luna-batch","name":"GPT-5.6 Luna (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.6-luna-20260709","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-6-luna-pro","slug":"openai-gpt-5-6-luna-pro","canonicalId":"openai-gpt-5-6-luna-pro","name":"GPT-5.6 Luna Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.6-luna-pro-20260709","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":2e-7,"completion":0.0000012},"inputPrice":0.19999999999999998,"outputPrice":1.2,"cachedInputPrice":null,"price":"$0.20","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-luna-pro","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-luna-pro","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":178,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-6-luna-pro","name":"GPT-5.6 Luna Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.6-luna-pro-20260709","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.19999999999999998,"outputPrice":1.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-6-luna-pro-batch","slug":"openai-gpt-5-6-luna-pro-batch","canonicalId":"openai-gpt-5-6-luna-pro-batch","name":"GPT-5.6 Luna Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.6-luna-pro-20260709","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":6e-7},"inputPrice":0.09999999999999999,"outputPrice":0.6,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-luna-pro:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-luna-pro:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":179,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-6-luna-pro-batch","name":"GPT-5.6 Luna Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.6-luna-pro-20260709","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-6-sol-batch","slug":"openai-gpt-5-6-sol-batch","canonicalId":"openai-gpt-5-6-sol-batch","name":"GPT-5.6 Sol (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.6-sol-20260709","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000005},"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":47,"coding":77.4,"agents":50.2,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-sol:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-sol:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":180,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-6-sol-batch","name":"GPT-5.6 Sol (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.6-sol-20260709","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-6-sol-pro","slug":"openai-gpt-5-6-sol-pro","canonicalId":"openai-gpt-5-6-sol-pro","name":"GPT-5.6 Sol Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.6-sol-pro-20260709","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.00001},"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-sol-pro","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-sol-pro","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":181,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-6-sol-pro","name":"GPT-5.6 Sol Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.6-sol-pro-20260709","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-6-sol-pro-batch","slug":"openai-gpt-5-6-sol-pro-batch","canonicalId":"openai-gpt-5-6-sol-pro-batch","name":"GPT-5.6 Sol Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.6-sol-pro-20260709","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000005},"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-sol-pro:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-sol-pro:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":182,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-6-sol-pro-batch","name":"GPT-5.6 Sol Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.6-sol-pro-20260709","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-6-terra","slug":"openai-gpt-5-6-terra","canonicalId":"openai-gpt-5-6-terra","name":"GPT-5.6 Terra","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.6-terra-20260709","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000012},"inputPrice":2,"outputPrice":12,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":42.1,"coding":76.7,"agents":43.2,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-terra","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-terra","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":183,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-6-terra","name":"GPT-5.6 Terra","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.6-terra-20260709","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":12,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-6-terra-batch","slug":"openai-gpt-5-6-terra-batch","canonicalId":"openai-gpt-5-6-terra-batch","name":"GPT-5.6 Terra (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.6-terra-20260709","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000006},"inputPrice":1,"outputPrice":6,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":42.1,"coding":76.7,"agents":43.2,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-terra:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-terra:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":184,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-6-terra-batch","name":"GPT-5.6 Terra (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.6-terra-20260709","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-6-terra-pro","slug":"openai-gpt-5-6-terra-pro","canonicalId":"openai-gpt-5-6-terra-pro","name":"GPT-5.6 Terra Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.6-terra-pro-20260709","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000012},"inputPrice":2,"outputPrice":12,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-terra-pro","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-terra-pro","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":185,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-6-terra-pro","name":"GPT-5.6 Terra Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.6-terra-pro-20260709","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":12,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-6-terra-pro-batch","slug":"openai-gpt-5-6-terra-pro-batch","canonicalId":"openai-gpt-5-6-terra-pro-batch","name":"GPT-5.6 Terra Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.6-terra-pro-20260709","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000006},"inputPrice":1,"outputPrice":6,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-terra-pro:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.6-terra-pro:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":186,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-6-terra-pro-batch","name":"GPT-5.6 Terra Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.6-terra-pro-20260709","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"x-ai-grok-4-5","slug":"x-ai-grok-4-5","canonicalId":"x-ai-grok-4-5","name":"Grok 4.5","provider":"xAI","family":null,"status":"active","variantType":"base","modelVersion":"x-ai/grok-4.5-20260708","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"500000","context":"500000","contextWindow":"500000","maxOutputTokens":"450000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000006},"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":38.8,"coding":72.4,"agents":41.2,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://x.ai/"},"pricing":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://x.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.x.ai/docs/models","catalogSourceUrl":"https://x.ai/","sourceUrl":"https://docs.x.ai/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=x.ai&sz=64","catalogRank":187,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"x-ai-grok-4-5","name":"Grok 4.5","provider":"xAI","family":null,"status":"active","variantType":"base","modelVersion":"x-ai/grok-4.5-20260708","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"500000","maxOutputTokens":"450000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://x.ai/"},"pricing":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://x.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"x-ai-grok-latest","slug":"x-ai-grok-latest","canonicalId":"x-ai-grok-latest","name":"Grok Latest","provider":"xAI","family":null,"status":"active","variantType":"base","modelVersion":"~x-ai/grok-latest","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"500000","context":"500000","contextWindow":"500000","maxOutputTokens":"450000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000006},"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://x.ai/"},"pricing":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://x.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.x.ai/docs/models","catalogSourceUrl":"https://x.ai/","sourceUrl":"https://docs.x.ai/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=x.ai&sz=64","catalogRank":188,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"x-ai-grok-latest","name":"Grok Latest","provider":"xAI","family":null,"status":"active","variantType":"base","modelVersion":"~x-ai/grok-latest","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"500000","maxOutputTokens":"450000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://x.ai/"},"pricing":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://x.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"aion-labs-aion-3-0","slug":"aion-labs-aion-3-0","canonicalId":"aion-labs-aion-3-0","name":"Aion-3.0","provider":"AionLabs","family":null,"status":"active","variantType":"base","modelVersion":"aion-labs/aion-3.0-20260707","modalities":["Text","Tools","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":0.000003,"completion":0.000006},"inputPrice":3,"outputPrice":6,"cachedInputPrice":null,"price":"$3.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aionlabs.ai/"},"pricing":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aionlabs.ai/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://aionlabs.ai/","sourceUrl":"https://aionlabs.ai/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=aionlabs.ai&sz=64","catalogRank":189,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"aion-labs-aion-3-0","name":"Aion-3.0","provider":"AionLabs","family":null,"status":"active","variantType":"base","modelVersion":"aion-labs/aion-3.0-20260707","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Tools","Reasoning"],"contextWindow":"131072","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":3,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aionlabs.ai/"},"pricing":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aionlabs.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"aion-labs-aion-3-0-mini","slug":"aion-labs-aion-3-0-mini","canonicalId":"aion-labs-aion-3-0-mini","name":"Aion-3.0-Mini","provider":"AionLabs","family":null,"status":"active","variantType":"fast","modelVersion":"aion-labs/aion-3.0-mini-20260707","modalities":["Text","Tools","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":7e-7,"completion":0.0000014},"inputPrice":0.7,"outputPrice":1.4,"cachedInputPrice":null,"price":"$0.70","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aionlabs.ai/"},"pricing":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aionlabs.ai/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://aionlabs.ai/","sourceUrl":"https://aionlabs.ai/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=aionlabs.ai&sz=64","catalogRank":190,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"aion-labs-aion-3-0-mini","name":"Aion-3.0-Mini","provider":"AionLabs","family":null,"status":"active","variantType":"fast","modelVersion":"aion-labs/aion-3.0-mini-20260707","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Tools","Reasoning"],"contextWindow":"131072","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.7,"outputPrice":1.4,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aionlabs.ai/"},"pricing":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aionlabs.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"tencent-hy3","slug":"tencent-hy3","canonicalId":"tencent-hy3","name":"Hy3","provider":"Tencent","family":null,"status":"active","variantType":"base","modelVersion":"tencent/hy3-20260706","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":1.32e-7,"completion":5.28e-7},"inputPrice":0.13199999999999998,"outputPrice":0.5279999999999999,"cachedInputPrice":null,"price":"$0.13","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"pricing":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"metrics":{},"fields":{}},"officialUrl":"https://cloud.tencent.com/product/hunyuan","catalogSourceUrl":"https://hunyuan.tencent.com/","sourceUrl":"https://cloud.tencent.com/product/hunyuan","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=tencent.com&sz=64","catalogRank":191,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"tencent-hy3","name":"Hy3","provider":"Tencent","family":null,"status":"active","variantType":"base","modelVersion":"tencent/hy3-20260706","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"128000","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.13199999999999998,"outputPrice":0.5279999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"pricing":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"poolside-laguna-xs-2-1","slug":"poolside-laguna-xs-2-1","canonicalId":"poolside-laguna-xs-2-1","name":"Laguna XS 2.1","provider":"Poolside","family":null,"status":"active","variantType":"base","modelVersion":"poolside/laguna-xs-2.1-20260625","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":6e-8,"completion":1.2e-7},"inputPrice":0.06,"outputPrice":0.12,"cachedInputPrice":null,"price":"$0.06","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://poolside.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://poolside.ai/"},"pricing":{"name":"Provider source","url":"https://poolside.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://poolside.ai/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://poolside.ai/","sourceUrl":"https://poolside.ai/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=poolside.ai&sz=64","catalogRank":192,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"poolside-laguna-xs-2-1","name":"Laguna XS 2.1","provider":"Poolside","family":null,"status":"active","variantType":"base","modelVersion":"poolside/laguna-xs-2.1-20260625","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.06,"outputPrice":0.12,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://poolside.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://poolside.ai/"},"pricing":{"name":"Provider source","url":"https://poolside.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://poolside.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"poolside-laguna-xs-2-1-free","slug":"poolside-laguna-xs-2-1-free","canonicalId":"poolside-laguna-xs-2-1-free","name":"Laguna XS 2.1 (free)","provider":"Poolside","family":null,"status":"active","variantType":"free","modelVersion":"poolside/laguna-xs-2.1-20260625","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://poolside.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://poolside.ai/"},"pricing":{"name":"Provider source","url":"https://poolside.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://poolside.ai/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://poolside.ai/","sourceUrl":"https://poolside.ai/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=poolside.ai&sz=64","catalogRank":193,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"poolside-laguna-xs-2-1-free","name":"Laguna XS 2.1 (free)","provider":"Poolside","family":null,"status":"active","variantType":"free","modelVersion":"poolside/laguna-xs-2.1-20260625","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://poolside.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://poolside.ai/"},"pricing":{"name":"Provider source","url":"https://poolside.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://poolside.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-sonnet-5-batch","slug":"anthropic-claude-sonnet-5-batch","canonicalId":"anthropic-claude-sonnet-5-batch","name":"Claude Sonnet 5 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-sonnet-5-20260630","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000005},"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":38.2,"coding":71.5,"agents":43.6,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":194,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-sonnet-5-batch","name":"Claude Sonnet 5 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-sonnet-5-20260630","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-1-flash-lite-image","slug":"google-gemini-3-1-flash-lite-image","canonicalId":"google-gemini-3-1-flash-lite-image","name":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-3.1-flash-lite-image-20260630","modalities":["Image","Text","Reasoning"],"context_length":"65536","context":"65536","contextWindow":"65536","maxOutputTokens":"58982","apiAvailable":true,"pricing":{"prompt":2.5e-7,"completion":0.0000015},"inputPrice":0.25,"outputPrice":1.5,"cachedInputPrice":null,"price":"$0.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":195,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-1-flash-lite-image","name":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-3.1-flash-lite-image-20260630","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text","Reasoning"],"contextWindow":"65536","maxOutputTokens":"58982","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.25,"outputPrice":1.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"sakana-fugu-ultra","slug":"sakana-fugu-ultra","canonicalId":"sakana-fugu-ultra","name":"Fugu Ultra","provider":"Sakana","family":null,"status":"active","variantType":"base","modelVersion":"sakana/fugu-ultra-20260615","modalities":["Text","Image","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000005,"completion":0.00003},"inputPrice":5,"outputPrice":30,"cachedInputPrice":null,"price":"$5.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://sakana.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://sakana.ai/"},"pricing":{"name":"Provider source","url":"https://sakana.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://sakana.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://sakana.ai/namazu-api/","catalogSourceUrl":"https://sakana.ai/","sourceUrl":"https://sakana.ai/namazu-api/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=sakana.ai&sz=64","catalogRank":196,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"sakana-fugu-ultra","name":"Fugu Ultra","provider":"Sakana","family":null,"status":"active","variantType":"base","modelVersion":"sakana/fugu-ultra-20260615","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":5,"outputPrice":30,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://sakana.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://sakana.ai/"},"pricing":{"name":"Provider source","url":"https://sakana.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://sakana.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-1-flash-image","slug":"google-gemini-3-1-flash-image","canonicalId":"google-gemini-3-1-flash-image","name":"Nano Banana 2 (Gemini 3.1 Flash Image)","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-3.1-flash-image-20260528","modalities":["Image","Text","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":5e-7,"completion":0.000003},"inputPrice":0.5,"outputPrice":3,"cachedInputPrice":null,"price":"$0.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":197,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-1-flash-image","name":"Nano Banana 2 (Gemini 3.1 Flash Image)","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-3.1-flash-image-20260528","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Image","Text","Reasoning"],"contextWindow":"131072","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.5,"outputPrice":3,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-pro-image","slug":"google-gemini-3-pro-image","canonicalId":"google-gemini-3-pro-image","name":"Nano Banana Pro (Gemini 3 Pro Image)","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemini-3-pro-image-20260528","modalities":["Image","Text","Tools","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000012},"inputPrice":2,"outputPrice":12,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":198,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-pro-image","name":"Nano Banana Pro (Gemini 3 Pro Image)","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemini-3-pro-image-20260528","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Image","Text","Tools","Reasoning"],"contextWindow":"131072","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":12,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"cohere-north-mini-code-free","slug":"cohere-north-mini-code-free","canonicalId":"cohere-north-mini-code-free","name":"North Mini Code (free)","provider":"Cohere","family":null,"status":"active","variantType":"free","modelVersion":"cohere/north-mini-code-20260617","modalities":["Text","Tools","Reasoning"],"context_length":"256000","context":"256000","contextWindow":"256000","maxOutputTokens":"64000","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":9.9,"coding":36.5,"agents":1.1,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://cohere.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://cohere.com/"},"pricing":{"name":"Provider source","url":"https://cohere.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://cohere.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.cohere.com/docs/models","catalogSourceUrl":"https://cohere.com/","sourceUrl":"https://docs.cohere.com/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=cohere.com&sz=64","catalogRank":199,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"cohere-north-mini-code-free","name":"North Mini Code (free)","provider":"Cohere","family":null,"status":"active","variantType":"free","modelVersion":"cohere/north-mini-code-20260617","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"256000","maxOutputTokens":"64000","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://cohere.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://cohere.com/"},"pricing":{"name":"Provider source","url":"https://cohere.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://cohere.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-5-2-batch","slug":"z-ai-glm-5-2-batch","canonicalId":"z-ai-glm-5-2-batch","name":"GLM 5.2 (batch)","provider":"Z.ai","family":null,"status":"active","variantType":"batch","modelVersion":"z-ai/glm-5.2-20260616","modalities":["Text","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":7e-7,"completion":0.0000022},"inputPrice":0.7,"outputPrice":2.2,"cachedInputPrice":null,"price":"$0.70","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":33.7,"coding":68.8,"agents":38.4,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-09-22","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":200,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-5-2-batch","name":"GLM 5.2 (batch)","provider":"Z.ai","family":null,"status":"active","variantType":"batch","modelVersion":"z-ai/glm-5.2-20260616","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.7,"outputPrice":2.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-5-2-free","slug":"z-ai-glm-5-2-free","canonicalId":"z-ai-glm-5-2-free","name":"GLM 5.2 (free)","provider":"Z.ai","family":null,"status":"active","variantType":"free","modelVersion":"z-ai/glm-5.2-20260616","modalities":["Text","Reasoning"],"context_length":"32768","context":"32768","contextWindow":"32768","maxOutputTokens":"29491","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":33.7,"coding":68.8,"agents":38.4,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-09-25","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":201,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-5-2-free","name":"GLM 5.2 (free)","provider":"Z.ai","family":null,"status":"active","variantType":"free","modelVersion":"z-ai/glm-5.2-20260616","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Reasoning"],"contextWindow":"32768","maxOutputTokens":"29491","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openrouter-fusion","slug":"openrouter-fusion","canonicalId":"openrouter-fusion","name":"Fusion","provider":"OpenRouter","family":null,"status":"active","variantType":"router","modelVersion":"openrouter/fusion","modalities":["Text"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":null,"apiAvailable":true,"pricing":{"prompt":null,"completion":null},"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"price":"N/A","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":null,"catalogRank":202,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openrouter-fusion","name":"Fusion","provider":"OpenRouter","family":null,"status":"active","variantType":"router","modelVersion":"openrouter/fusion","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text"],"contextWindow":"1000000","maxOutputTokens":null,"apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"moonshotai-kimi-k2-7-code","slug":"moonshotai-kimi-k2-7-code","canonicalId":"moonshotai-kimi-k2-7-code","name":"Kimi K2.7 Code","provider":"Moonshot AI","family":null,"status":"active","variantType":"base","modelVersion":"moonshotai/kimi-k2.7-code-20260612","modalities":["Text","Image","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":6.712e-7,"completion":0.00000335},"inputPrice":0.6712,"outputPrice":3.35,"cachedInputPrice":null,"price":"$0.67","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":25.8,"coding":60.8,"agents":21,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://platform.moonshot.ai/docs/guide/models","catalogSourceUrl":"https://moonshot.ai/","sourceUrl":"https://platform.moonshot.ai/docs/guide/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=moonshot.ai&sz=64","catalogRank":203,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"moonshotai-kimi-k2-7-code","name":"Kimi K2.7 Code","provider":"Moonshot AI","family":null,"status":"active","variantType":"base","modelVersion":"moonshotai/kimi-k2.7-code-20260612","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.6712,"outputPrice":3.35,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"moonshotai-kimi-k2-7-code-batch","slug":"moonshotai-kimi-k2-7-code-batch","canonicalId":"moonshotai-kimi-k2-7-code-batch","name":"Kimi K2.7 Code (batch)","provider":"Moonshot AI","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text","Image","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":9.499999999999999e-7,"completion":0.000004},"inputPrice":0.95,"outputPrice":4,"cachedInputPrice":null,"price":"$0.95","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":43,"coding":60.8,"agents":30.3,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://moonshot.ai/","catalogSourceUrl":"https://moonshot.ai/","sourceUrl":"https://moonshot.ai/","sourceUpdatedAt":{},"updated":"2026-08-27","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=moonshot.ai&sz=64","catalogRank":204,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"moonshotai-kimi-k2-7-code-batch","name":"Kimi K2.7 Code (batch)","provider":"Moonshot AI","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":null,"apiAvailable":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"inputPrice":0.95,"outputPrice":4,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-fable-5-batch","slug":"anthropic-claude-fable-5-batch","canonicalId":"anthropic-claude-fable-5-batch","name":"Claude Fable 5 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-5-fable-20260609","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000005,"completion":0.000025},"inputPrice":5,"outputPrice":25,"cachedInputPrice":null,"price":"$5.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":49.6,"coding":76.5,"agents":50.7,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":205,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-fable-5-batch","name":"Claude Fable 5 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-5-fable-20260609","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":5,"outputPrice":25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-fable-latest","slug":"anthropic-claude-fable-latest","canonicalId":"anthropic-claude-fable-latest","name":"Claude Fable Latest","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"~anthropic/claude-fable-latest","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00001,"completion":0.00005},"inputPrice":10,"outputPrice":50,"cachedInputPrice":null,"price":"$10.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":206,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-fable-latest","name":"Claude Fable Latest","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"~anthropic/claude-fable-latest","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":10,"outputPrice":50,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"nvidia-nemotron-3-ultra-550b-a55b","slug":"nvidia-nemotron-3-ultra-550b-a55b","canonicalId":"nvidia-nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra","provider":"NVIDIA","family":null,"status":"active","variantType":"base","modelVersion":"nvidia/nemotron-3-ultra-550b-a55b-20260604","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"182520","apiAvailable":true,"pricing":{"prompt":6e-7,"completion":0.0000024},"inputPrice":0.6,"outputPrice":2.4,"cachedInputPrice":null,"price":"$0.60","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":22.9,"coding":49.3,"agents":20.1,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}},"officialUrl":"https://build.nvidia.com/explore/discover","catalogSourceUrl":"https://nvidia.com/","sourceUrl":"https://build.nvidia.com/explore/discover","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=nvidia.com&sz=64","catalogRank":207,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"nvidia-nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra","provider":"NVIDIA","family":null,"status":"active","variantType":"base","modelVersion":"nvidia/nemotron-3-ultra-550b-a55b-20260604","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"182520","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.6,"outputPrice":2.4,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"nvidia-nemotron-3-ultra-550b-a55b-batch","slug":"nvidia-nemotron-3-ultra-550b-a55b-batch","canonicalId":"nvidia-nemotron-3-ultra-550b-a55b-batch","name":"Nemotron 3 Ultra (batch)","provider":"NVIDIA","family":null,"status":"active","variantType":"batch","modelVersion":"nvidia/nemotron-3-ultra-550b-a55b-20260604","modalities":["Text","Tools","Reasoning"],"context_length":"512288","context":"512288","contextWindow":"512288","maxOutputTokens":"461059","apiAvailable":true,"pricing":{"prompt":6e-7,"completion":0.0000036},"inputPrice":0.6,"outputPrice":3.5999999999999996,"cachedInputPrice":null,"price":"$0.60","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":38.3,"coding":49.3,"agents":27.5,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}},"officialUrl":"https://build.nvidia.com/explore/discover","catalogSourceUrl":"https://nvidia.com/","sourceUrl":"https://build.nvidia.com/explore/discover","sourceUpdatedAt":{},"updated":"2026-09-02","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=nvidia.com&sz=64","catalogRank":208,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"nvidia-nemotron-3-ultra-550b-a55b-batch","name":"Nemotron 3 Ultra (batch)","provider":"NVIDIA","family":null,"status":"active","variantType":"batch","modelVersion":"nvidia/nemotron-3-ultra-550b-a55b-20260604","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"512288","maxOutputTokens":"461059","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.6,"outputPrice":3.5999999999999996,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"nvidia-nemotron-3-ultra-550b-a55b-free","slug":"nvidia-nemotron-3-ultra-550b-a55b-free","canonicalId":"nvidia-nemotron-3-ultra-550b-a55b-free","name":"Nemotron 3 Ultra (free)","provider":"NVIDIA","family":null,"status":"active","variantType":"free","modelVersion":"nvidia/nemotron-3-ultra-550b-a55b-20260604","modalities":["Text","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":22.9,"coding":49.3,"agents":20.1,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}},"officialUrl":"https://build.nvidia.com/explore/discover","catalogSourceUrl":"https://nvidia.com/","sourceUrl":"https://build.nvidia.com/explore/discover","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=nvidia.com&sz=64","catalogRank":209,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"nvidia-nemotron-3-ultra-550b-a55b-free","name":"Nemotron 3 Ultra (free)","provider":"NVIDIA","family":null,"status":"active","variantType":"free","modelVersion":"nvidia/nemotron-3-ultra-550b-a55b-20260604","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"65536","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"nvidia-nemotron-3-5-content-safety","slug":"nvidia-nemotron-3-5-content-safety","canonicalId":"nvidia-nemotron-3-5-content-safety","name":"Nemotron 3.5 Content Safety","provider":"NVIDIA","family":null,"status":"active","variantType":"base","modelVersion":"nvidia/nemotron-3.5-content-safety-20260604","modalities":["Text","Image","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"pricing":{"prompt":2e-7,"completion":2e-7},"inputPrice":0.19999999999999998,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"price":"$0.20","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}},"officialUrl":"https://build.nvidia.com/explore/discover","catalogSourceUrl":"https://nvidia.com/","sourceUrl":"https://build.nvidia.com/explore/discover","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=nvidia.com&sz=64","catalogRank":210,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"nvidia-nemotron-3-5-content-safety","name":"Nemotron 3.5 Content Safety","provider":"NVIDIA","family":null,"status":"active","variantType":"base","modelVersion":"nvidia/nemotron-3.5-content-safety-20260604","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Reasoning"],"contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.19999999999999998,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"nvidia-nemotron-3-5-content-safety-free","slug":"nvidia-nemotron-3-5-content-safety-free","canonicalId":"nvidia-nemotron-3-5-content-safety-free","name":"Nemotron 3.5 Content Safety (free)","provider":"NVIDIA","family":null,"status":"active","variantType":"free","modelVersion":"nvidia/nemotron-3.5-content-safety-20260604","modalities":["Text","Image","Reasoning"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"8192","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}},"officialUrl":"https://build.nvidia.com/explore/discover","catalogSourceUrl":"https://nvidia.com/","sourceUrl":"https://build.nvidia.com/explore/discover","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=nvidia.com&sz=64","catalogRank":211,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"nvidia-nemotron-3-5-content-safety-free","name":"Nemotron 3.5 Content Safety (free)","provider":"NVIDIA","family":null,"status":"active","variantType":"free","modelVersion":"nvidia/nemotron-3.5-content-safety-20260604","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Reasoning"],"contextWindow":"128000","maxOutputTokens":"8192","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-7-plus","slug":"qwen-qwen3-7-plus","canonicalId":"qwen-qwen3-7-plus","name":"Qwen3.7 Plus","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.7-plus-20260602","modalities":["Text","Image","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":3.2e-7,"completion":0.00000128},"inputPrice":0.32,"outputPrice":1.28,"cachedInputPrice":null,"price":"$0.32","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":25.2,"coding":55.9,"agents":17.5,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":212,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-7-plus","name":"Qwen3.7 Plus","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.7-plus-20260602","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.32,"outputPrice":1.28,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"minimax-minimax-m3-batch","slug":"minimax-minimax-m3-batch","canonicalId":"minimax-minimax-m3-batch","name":"MiniMax M3 (batch)","provider":"MiniMax","family":null,"status":"active","variantType":"batch","modelVersion":"minimax/minimax-m3-20260531","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"524288","context":"524288","contextWindow":"524288","maxOutputTokens":"471859","apiAvailable":true,"pricing":{"prompt":3e-7,"completion":0.0000012},"inputPrice":0.3,"outputPrice":1.2,"cachedInputPrice":null,"price":"$0.30","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":29.2,"coding":58.6,"agents":29.5,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}},"officialUrl":"https://platform.minimax.io/docs/guides/models","catalogSourceUrl":"https://minimax.io/","sourceUrl":"https://platform.minimax.io/docs/guides/models","sourceUpdatedAt":{},"updated":"2026-09-21","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=minimax.io&sz=64","catalogRank":213,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"minimax-minimax-m3-batch","name":"MiniMax M3 (batch)","provider":"MiniMax","family":null,"status":"active","variantType":"batch","modelVersion":"minimax/minimax-m3-20260531","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"524288","maxOutputTokens":"471859","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.3,"outputPrice":1.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"minimax-minimax-m3-free","slug":"minimax-minimax-m3-free","canonicalId":"minimax-minimax-m3-free","name":"MiniMax M3 (free)","provider":"MiniMax","family":null,"status":"active","variantType":"free","modelVersion":"minimax/minimax-m3-20260531","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":35.7,"coding":58.6,"agents":31,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}},"officialUrl":"https://platform.minimax.io/docs/guides/models","catalogSourceUrl":"https://minimax.io/","sourceUrl":"https://platform.minimax.io/docs/guides/models","sourceUpdatedAt":{},"updated":"2026-09-07","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=minimax.io&sz=64","catalogRank":214,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"minimax-minimax-m3-free","name":"MiniMax M3 (free)","provider":"MiniMax","family":null,"status":"active","variantType":"free","modelVersion":"minimax/minimax-m3-20260531","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"stepfun-step-3-7-flash","slug":"stepfun-step-3-7-flash","canonicalId":"stepfun-step-3-7-flash","name":"Step 3.7 Flash","provider":"StepFun","family":null,"status":"active","variantType":"fast","modelVersion":"stepfun/step-3.7-flash-20260528","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"230400","apiAvailable":true,"pricing":{"prompt":2e-7,"completion":0.00000115},"inputPrice":0.19999999999999998,"outputPrice":1.15,"cachedInputPrice":null,"price":"$0.20","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":19.5,"coding":39.6,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://stepfun.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://stepfun.com/"},"pricing":{"name":"Provider source","url":"https://stepfun.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://stepfun.com/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://stepfun.com/","sourceUrl":"https://stepfun.com/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=stepfun.com&sz=64","catalogRank":215,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"stepfun-step-3-7-flash","name":"Step 3.7 Flash","provider":"StepFun","family":null,"status":"active","variantType":"fast","modelVersion":"stepfun/step-3.7-flash-20260528","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"230400","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.19999999999999998,"outputPrice":1.15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://stepfun.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://stepfun.com/"},"pricing":{"name":"Provider source","url":"https://stepfun.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://stepfun.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-opus-4-8-batch","slug":"anthropic-claude-opus-4-8-batch","canonicalId":"anthropic-claude-opus-4-8-batch","name":"Claude Opus 4.8 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-4.8-opus-20260528","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.0000125},"inputPrice":2.5,"outputPrice":12.5,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":41.8,"coding":74.3,"agents":41.9,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":216,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-opus-4-8-batch","name":"Claude Opus 4.8 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-4.8-opus-20260528","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2.5,"outputPrice":12.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-opus-4-8-fast","slug":"anthropic-claude-opus-4-8-fast","canonicalId":"anthropic-claude-opus-4-8-fast","name":"Claude Opus 4.8 (Fast)","provider":"Anthropic","family":null,"status":"active","variantType":"fast","modelVersion":"anthropic/claude-4.8-opus-fast-20260528","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00001,"completion":0.00005},"inputPrice":10,"outputPrice":50,"cachedInputPrice":null,"price":"$10.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-09-01","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":217,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-opus-4-8-fast","name":"Claude Opus 4.8 (Fast)","provider":"Anthropic","family":null,"status":"active","variantType":"fast","modelVersion":"anthropic/claude-4.8-opus-fast-20260528","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":10,"outputPrice":50,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-7-max","slug":"qwen-qwen3-7-max","canonicalId":"qwen-qwen3-7-max","name":"Qwen3.7 Max","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.7-max-20260520","modalities":["Text","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":0.000001475,"completion":0.000004425},"inputPrice":1.475,"outputPrice":4.425,"cachedInputPrice":null,"price":"$1.48","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":29.5,"coding":66,"agents":22.5,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":218,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-7-max","name":"Qwen3.7 Max","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.7-max-20260520","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.475,"outputPrice":4.425,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"x-ai-grok-build-0-1","slug":"x-ai-grok-build-0-1","canonicalId":"x-ai-grok-build-0-1","name":"Grok Build 0.1","provider":"xAI","family":null,"status":"active","variantType":"base","modelVersion":"x-ai/grok-build-0.1-20260520","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"256000","context":"256000","contextWindow":"256000","maxOutputTokens":"230400","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000002},"inputPrice":1,"outputPrice":2,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":27.2,"coding":51.5,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://x.ai/"},"pricing":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://x.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.x.ai/docs/models","catalogSourceUrl":"https://x.ai/","sourceUrl":"https://docs.x.ai/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=x.ai&sz=64","catalogRank":219,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"x-ai-grok-build-0-1","name":"Grok Build 0.1","provider":"xAI","family":null,"status":"active","variantType":"base","modelVersion":"x-ai/grok-build-0.1-20260520","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"256000","maxOutputTokens":"230400","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://x.ai/"},"pricing":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://x.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-5-flash-batch","slug":"google-gemini-3-5-flash-batch","canonicalId":"google-gemini-3-5-flash-batch","name":"Gemini 3.5 Flash (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-3.5-flash-20260519","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":7.5e-7,"completion":0.0000045},"inputPrice":0.75,"outputPrice":4.5,"cachedInputPrice":null,"price":"$0.75","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":33.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":220,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-5-flash-batch","name":"Gemini 3.5 Flash (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-3.5-flash-20260519","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.75,"outputPrice":4.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-opus-4-7-fast","slug":"anthropic-claude-opus-4-7-fast","canonicalId":"anthropic-claude-opus-4-7-fast","name":"Claude Opus 4.7 (Fast)","provider":"Anthropic","family":null,"status":"active","variantType":"fast","modelVersion":"anthropic/claude-4.7-opus-fast-20260512","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00003,"completion":0.00015},"inputPrice":30,"outputPrice":150,"cachedInputPrice":null,"price":"$30.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-09-01","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":221,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-opus-4-7-fast","name":"Claude Opus 4.7 (Fast)","provider":"Anthropic","family":null,"status":"active","variantType":"fast","modelVersion":"anthropic/claude-4.7-opus-fast-20260512","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":30,"outputPrice":150,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"perceptron-perceptron-mk1","slug":"perceptron-perceptron-mk1","canonicalId":"perceptron-perceptron-mk1","name":"Perceptron Mk1","provider":"Perceptron","family":null,"status":"active","variantType":"base","modelVersion":"perceptron/perceptron-mk1-20260512","modalities":["Text","Image","Video","Reasoning"],"context_length":"32768","context":"32768","contextWindow":"32768","maxOutputTokens":"8192","apiAvailable":true,"pricing":{"prompt":1.5e-7,"completion":0.0000015},"inputPrice":0.15,"outputPrice":1.5,"cachedInputPrice":null,"price":"$0.15","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":null,"catalogRank":222,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"perceptron-perceptron-mk1","name":"Perceptron Mk1","provider":"Perceptron","family":null,"status":"active","variantType":"base","modelVersion":"perceptron/perceptron-mk1-20260512","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","Reasoning"],"contextWindow":"32768","maxOutputTokens":"8192","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.15,"outputPrice":1.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-1-flash-lite","slug":"google-gemini-3-1-flash-lite","canonicalId":"google-gemini-3-1-flash-lite","name":"Gemini 3.1 Flash Lite","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-3.1-flash-lite-20260507","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":2.5e-7,"completion":0.0000015},"inputPrice":0.25,"outputPrice":1.5,"cachedInputPrice":null,"price":"$0.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":223,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-1-flash-lite","name":"Gemini 3.1 Flash Lite","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-3.1-flash-lite-20260507","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.25,"outputPrice":1.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-1-flash-lite-batch","slug":"google-gemini-3-1-flash-lite-batch","canonicalId":"google-gemini-3-1-flash-lite-batch","name":"Gemini 3.1 Flash Lite (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-3.1-flash-lite-20260507","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":1.25e-7,"completion":7.5e-7},"inputPrice":0.125,"outputPrice":0.75,"cachedInputPrice":null,"price":"$0.13","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":224,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-1-flash-lite-batch","name":"Gemini 3.1 Flash Lite (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-3.1-flash-lite-20260507","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.125,"outputPrice":0.75,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-chat-latest","slug":"openai-gpt-chat-latest","canonicalId":"openai-gpt-chat-latest","name":"GPT Chat Latest","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-chat-latest-20260505","modalities":["Text","Image","File","Tools"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000005,"completion":0.00003},"inputPrice":5,"outputPrice":30,"cachedInputPrice":null,"price":"$5.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-chat-latest","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-chat-latest","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":225,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-chat-latest","name":"GPT Chat Latest","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-chat-latest-20260505","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":5,"outputPrice":30,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"ibm-granite-granite-4-1-8b","slug":"ibm-granite-granite-4-1-8b","canonicalId":"ibm-granite-granite-4-1-8b","name":"Granite 4.1 8B","provider":"IBM","family":null,"status":"active","variantType":"base","modelVersion":"ibm-granite/granite-4.1-8b-20260429","modalities":["Text","Tools"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"pricing":{"prompt":5e-8,"completion":1e-7},"inputPrice":0.049999999999999996,"outputPrice":0.09999999999999999,"cachedInputPrice":null,"price":"$0.05","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":0,"coding":9.5,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ibm.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ibm.com/"},"pricing":{"name":"Provider source","url":"https://ibm.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ibm.com/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://ibm.com/","sourceUrl":"https://ibm.com/","sourceUpdatedAt":{},"updated":"2026-09-04","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=ibm.com&sz=64","catalogRank":226,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"ibm-granite-granite-4-1-8b","name":"Granite 4.1 8B","provider":"IBM","family":null,"status":"active","variantType":"base","modelVersion":"ibm-granite/granite-4.1-8b-20260429","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools"],"contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.049999999999999996,"outputPrice":0.09999999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ibm.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ibm.com/"},"pricing":{"name":"Provider source","url":"https://ibm.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ibm.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-mistral-medium-3-5","slug":"mistralai-mistral-medium-3-5","canonicalId":"mistralai-mistral-medium-3-5","name":"Mistral Medium 3.5","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-medium-3.5-20260430","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"pricing":{"prompt":0.0000015,"completion":0.0000075},"inputPrice":1.5,"outputPrice":7.5,"cachedInputPrice":null,"price":"$1.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":14.2,"coding":46.9,"agents":7,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":227,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-mistral-medium-3-5","name":"Mistral Medium 3.5","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-medium-3.5-20260430","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":1.5,"outputPrice":7.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-mistral-medium-3-5-batch","slug":"mistralai-mistral-medium-3-5-batch","canonicalId":"mistralai-mistral-medium-3-5-batch","name":"Mistral Medium 3.5 (batch)","provider":"Mistral","family":null,"status":"active","variantType":"batch","modelVersion":"mistralai/mistral-medium-3.5-20260430","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"pricing":{"prompt":7.5e-7,"completion":0.00000375},"inputPrice":0.75,"outputPrice":3.75,"cachedInputPrice":null,"price":"$0.75","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":14.2,"coding":46.9,"agents":7,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":228,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-mistral-medium-3-5-batch","name":"Mistral Medium 3.5 (batch)","provider":"Mistral","family":null,"status":"active","variantType":"batch","modelVersion":"mistralai/mistral-medium-3.5-20260430","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.75,"outputPrice":3.75,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"x-ai-grok-4-3","slug":"x-ai-grok-4-3","canonicalId":"x-ai-grok-4-3","name":"Grok 4.3","provider":"xAI","family":null,"status":"active","variantType":"base","modelVersion":"x-ai/grok-4.3-20260430","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"900000","apiAvailable":true,"pricing":{"prompt":0.00000125,"completion":0.0000025},"inputPrice":1.25,"outputPrice":2.5,"cachedInputPrice":null,"price":"$1.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":24.9,"coding":42.2,"agents":15.5,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://x.ai/"},"pricing":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://x.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.x.ai/docs/models","catalogSourceUrl":"https://x.ai/","sourceUrl":"https://docs.x.ai/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=x.ai&sz=64","catalogRank":229,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"x-ai-grok-4-3","name":"Grok 4.3","provider":"xAI","family":null,"status":"active","variantType":"base","modelVersion":"x-ai/grok-4.3-20260430","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"900000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.25,"outputPrice":2.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://x.ai/"},"pricing":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://x.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"x-ai-grok-4-3-batch","slug":"x-ai-grok-4-3-batch","canonicalId":"x-ai-grok-4-3-batch","name":"Grok 4.3 (batch)","provider":"xAI","family":null,"status":"active","variantType":"batch","modelVersion":"x-ai/grok-4.3-20260430","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"900000","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000002},"inputPrice":1,"outputPrice":2,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":24.9,"coding":42.2,"agents":15.5,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://x.ai/"},"pricing":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://x.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.x.ai/docs/models","catalogSourceUrl":"https://x.ai/","sourceUrl":"https://docs.x.ai/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":null,"providerIconUrl":"https://www.google.com/s2/favicons?domain=x.ai&sz=64","catalogRank":230,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"x-ai-grok-4-3-batch","name":"Grok 4.3 (batch)","provider":"xAI","family":null,"status":"active","variantType":"batch","modelVersion":"x-ai/grok-4.3-20260430","releaseDate":{},"knowledgeCutoff":null,"license":null,"modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"900000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://x.ai/"},"pricing":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://x.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"nvidia-nemotron-3-nano-omni-30b-a3b-reasoning-free","slug":"nvidia-nemotron-3-nano-omni-30b-a3b-reasoning-free","canonicalId":"nvidia-nemotron-3-nano-omni-30b-a3b-reasoning-free","name":"Nemotron 3 Nano Omni (free)","provider":"NVIDIA","family":null,"status":"active","variantType":"free","modelVersion":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428","modalities":["Text","Audio","Image","Video","Tools","Reasoning"],"context_length":"256000","context":"256000","contextWindow":"256000","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":10.3,"coding":13.8,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}},"officialUrl":"https://build.nvidia.com/explore/discover","catalogSourceUrl":"https://nvidia.com/","sourceUrl":"https://build.nvidia.com/explore/discover","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=nvidia.com&sz=64","catalogRank":231,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"nvidia-nemotron-3-nano-omni-30b-a3b-reasoning-free","name":"Nemotron 3 Nano Omni (free)","provider":"NVIDIA","family":null,"status":"active","variantType":"free","modelVersion":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Audio","Image","Video","Tools","Reasoning"],"contextWindow":"256000","maxOutputTokens":"65536","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-haiku-latest","slug":"anthropic-claude-haiku-latest","canonicalId":"anthropic-claude-haiku-latest","name":"Claude Haiku Latest","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"~anthropic/claude-haiku-latest","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":5e-7},"inputPrice":0.09999999999999999,"outputPrice":0.5,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":232,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-haiku-latest","name":"Claude Haiku Latest","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"~anthropic/claude-haiku-latest","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-sonnet-latest","slug":"anthropic-claude-sonnet-latest","canonicalId":"anthropic-claude-sonnet-latest","name":"Claude Sonnet Latest","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"~anthropic/claude-sonnet-latest","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.00001},"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":233,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-sonnet-latest","name":"Claude Sonnet Latest","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"~anthropic/claude-sonnet-latest","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-flash-latest","slug":"google-gemini-flash-latest","canonicalId":"google-gemini-flash-latest","name":"Gemini Flash Latest","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"~google/gemini-flash-latest","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":7.5e-7,"completion":0.00000375},"inputPrice":0.75,"outputPrice":3.75,"cachedInputPrice":null,"price":"$0.75","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":234,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-flash-latest","name":"Gemini Flash Latest","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"~google/gemini-flash-latest","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.75,"outputPrice":3.75,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-pro-latest","slug":"google-gemini-pro-latest","canonicalId":"google-gemini-pro-latest","name":"Gemini Pro Latest","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"~google/gemini-pro-latest","modalities":["Audio","File","Image","Text","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000012},"inputPrice":2,"outputPrice":12,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":235,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-pro-latest","name":"Gemini Pro Latest","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"~google/gemini-pro-latest","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Audio","File","Image","Text","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":12,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"moonshotai-kimi-latest","slug":"moonshotai-kimi-latest","canonicalId":"moonshotai-kimi-latest","name":"Kimi Latest","provider":"Moonshot AI","family":null,"status":"active","variantType":"base","modelVersion":"~moonshotai/kimi-latest","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"pricing":{"prompt":7e-7,"completion":0.0000135},"inputPrice":0.7,"outputPrice":13.5,"cachedInputPrice":null,"price":"$0.70","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://platform.moonshot.ai/docs/guide/models","catalogSourceUrl":"https://moonshot.ai/","sourceUrl":"https://platform.moonshot.ai/docs/guide/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=moonshot.ai&sz=64","catalogRank":236,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"moonshotai-kimi-latest","name":"Kimi Latest","provider":"Moonshot AI","family":null,"status":"active","variantType":"base","modelVersion":"~moonshotai/kimi-latest","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943718","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.7,"outputPrice":13.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-latest","slug":"openai-gpt-latest","canonicalId":"openai-gpt-latest","name":"GPT Latest","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"~openai/gpt-latest","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.00001},"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-latest","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-latest","sourceUpdatedAt":{},"updated":"2026-09-11","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":237,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-latest","name":"GPT Latest","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"~openai/gpt-latest","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-mini-latest","slug":"openai-gpt-mini-latest","canonicalId":"openai-gpt-mini-latest","name":"GPT Mini Latest","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"~openai/gpt-mini-latest","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":7.5e-7,"completion":0.0000045},"inputPrice":0.75,"outputPrice":4.5,"cachedInputPrice":null,"price":"$0.75","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-mini-latest","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-mini-latest","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":238,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-mini-latest","name":"GPT Mini Latest","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"~openai/gpt-mini-latest","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.75,"outputPrice":4.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-5-plus-20260420","slug":"qwen-qwen3-5-plus-20260420","canonicalId":"qwen-qwen3-5-plus-20260420","name":"Qwen3.5 Plus 2026-04-20","provider":"Qwen","family":null,"status":"active","variantType":"dated","modelVersion":"qwen/qwen3.5-plus-20260420","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":3e-7,"completion":0.0000018},"inputPrice":0.3,"outputPrice":1.7999999999999998,"cachedInputPrice":null,"price":"$0.30","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":239,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-5-plus-20260420","name":"Qwen3.5 Plus 2026-04-20","provider":"Qwen","family":null,"status":"active","variantType":"dated","modelVersion":"qwen/qwen3.5-plus-20260420","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.3,"outputPrice":1.7999999999999998,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-6-27b","slug":"qwen-qwen3-6-27b","canonicalId":"qwen-qwen3-6-27b","name":"Qwen3.6 27B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.6-27b-20260422","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"81920","apiAvailable":true,"pricing":{"prompt":3.2e-7,"completion":0.0000032},"inputPrice":0.32,"outputPrice":3.1999999999999997,"cachedInputPrice":null,"price":"$0.32","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":21.4,"coding":53.7,"agents":18.5,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":240,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-6-27b","name":"Qwen3.6 27B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.6-27b-20260422","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"81920","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.32,"outputPrice":3.1999999999999997,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-6-35b-a3b","slug":"qwen-qwen3-6-35b-a3b","canonicalId":"qwen-qwen3-6-35b-a3b","name":"Qwen3.6 35B A3B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.6-35b-a3b-20260415","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":9.499999999999999e-7},"inputPrice":0.09999999999999999,"outputPrice":0.95,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":18.2,"coding":41.9,"agents":13.1,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":241,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-6-35b-a3b","name":"Qwen3.6 35B A3B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.6-35b-a3b-20260415","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"65536","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.95,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-6-flash","slug":"qwen-qwen3-6-flash","canonicalId":"qwen-qwen3-6-flash","name":"Qwen3.6 Flash","provider":"Qwen","family":null,"status":"active","variantType":"fast","modelVersion":"qwen/qwen3.6-flash","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":1.875e-7,"completion":0.000001125},"inputPrice":0.1875,"outputPrice":1.125,"cachedInputPrice":null,"price":"$0.19","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":242,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-6-flash","name":"Qwen3.6 Flash","provider":"Qwen","family":null,"status":"active","variantType":"fast","modelVersion":"qwen/qwen3.6-flash","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.1875,"outputPrice":1.125,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-v4-flash","slug":"deepseek-deepseek-v4-flash","canonicalId":"deepseek-deepseek-v4-flash","name":"DeepSeek V4 Flash 0423","provider":"DeepSeek","family":null,"status":"active","variantType":"fast","modelVersion":"deepseek/deepseek-v4-flash-20260423","modalities":["Text","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"943717","apiAvailable":true,"pricing":{"prompt":9.1e-8,"completion":1.82e-7},"inputPrice":0.091,"outputPrice":0.182,"cachedInputPrice":null,"price":"$0.09","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":24.4,"coding":52,"agents":26.3,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":243,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-v4-flash","name":"DeepSeek V4 Flash 0423","provider":"DeepSeek","family":null,"status":"active","variantType":"fast","modelVersion":"deepseek/deepseek-v4-flash-20260423","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"943717","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.091,"outputPrice":0.182,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-v4-pro","slug":"deepseek-deepseek-v4-pro","canonicalId":"deepseek-deepseek-v4-pro","name":"DeepSeek V4 Pro 0423","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"deepseek/deepseek-v4-pro-20260423","modalities":["Text","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"384000","apiAvailable":true,"pricing":{"prompt":9.5526e-7,"completion":0.00000191052},"inputPrice":0.9552599999999999,"outputPrice":1.9105199999999998,"cachedInputPrice":null,"price":"$0.96","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":30.4,"coding":59.4,"agents":26.3,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":244,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-v4-pro","name":"DeepSeek V4 Pro 0423","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"deepseek/deepseek-v4-pro-20260423","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"384000","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.9552599999999999,"outputPrice":1.9105199999999998,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-5-batch","slug":"openai-gpt-5-5-batch","canonicalId":"openai-gpt-5-5-batch","name":"GPT-5.5 (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.5-20260423","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.000015},"inputPrice":2.5,"outputPrice":15,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":38.4,"coding":74.9,"agents":36.4,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.5:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.5:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":245,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-5-batch","name":"GPT-5.5 (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.5-20260423","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2.5,"outputPrice":15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-5-pro-batch","slug":"openai-gpt-5-5-pro-batch","canonicalId":"openai-gpt-5-5-pro-batch","name":"GPT-5.5 Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.5-pro-20260423","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000015,"completion":0.00009},"inputPrice":15,"outputPrice":90,"cachedInputPrice":null,"price":"$15.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.5-pro:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.5-pro:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":246,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-5-pro-batch","name":"GPT-5.5 Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.5-pro-20260423","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":15,"outputPrice":90,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"tencent-hy3-preview","slug":"tencent-hy3-preview","canonicalId":"tencent-hy3-preview","name":"Hy3 preview","provider":"Tencent","family":null,"status":"active","variantType":"preview","modelVersion":"tencent/hy3-preview-20260421","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":1.8e-7,"completion":6e-7},"inputPrice":0.18,"outputPrice":0.6,"cachedInputPrice":null,"price":"$0.18","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":25.3,"coding":58.8,"agents":24.1,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"pricing":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"metrics":{},"fields":{}},"officialUrl":"https://cloud.tencent.com/product/hunyuan","catalogSourceUrl":"https://hunyuan.tencent.com/","sourceUrl":"https://cloud.tencent.com/product/hunyuan","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=tencent.com&sz=64","catalogRank":247,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"tencent-hy3-preview","name":"Hy3 preview","provider":"Tencent","family":null,"status":"active","variantType":"preview","modelVersion":"tencent/hy3-preview-20260421","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.18,"outputPrice":0.6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"pricing":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"xiaomi-mimo-v2-5","slug":"xiaomi-mimo-v2-5","canonicalId":"xiaomi-mimo-v2-5","name":"MiMo-V2.5","provider":"Xiaomi","family":null,"status":"active","variantType":"base","modelVersion":"xiaomi/mimo-v2.5-20260422","modalities":["Text","Audio","Image","Video","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":1.4e-7,"completion":2.8e-7},"inputPrice":0.14,"outputPrice":0.28,"cachedInputPrice":null,"price":"$0.14","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":25.2,"coding":56.8,"agents":15.8,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mi.com/"},"pricing":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mi.com/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://mi.com/","sourceUrl":"https://mi.com/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=mi.com&sz=64","catalogRank":248,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"xiaomi-mimo-v2-5","name":"MiMo-V2.5","provider":"Xiaomi","family":null,"status":"active","variantType":"base","modelVersion":"xiaomi/mimo-v2.5-20260422","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Audio","Image","Video","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"131072","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.14,"outputPrice":0.28,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mi.com/"},"pricing":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mi.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"xiaomi-mimo-v2-5-pro","slug":"xiaomi-mimo-v2-5-pro","canonicalId":"xiaomi-mimo-v2-5-pro","name":"MiMo-V2.5-Pro","provider":"Xiaomi","family":null,"status":"active","variantType":"base","modelVersion":"xiaomi/mimo-v2.5-pro-20260422","modalities":["Text","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":4.35e-7,"completion":8.7e-7},"inputPrice":0.435,"outputPrice":0.87,"cachedInputPrice":null,"price":"$0.43","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":26,"coding":60.2,"agents":21.3,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mi.com/"},"pricing":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mi.com/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://mi.com/","sourceUrl":"https://mi.com/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=mi.com&sz=64","catalogRank":249,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"xiaomi-mimo-v2-5-pro","name":"MiMo-V2.5-Pro","provider":"Xiaomi","family":null,"status":"active","variantType":"base","modelVersion":"xiaomi/mimo-v2.5-pro-20260422","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"131072","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.435,"outputPrice":0.87,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mi.com/"},"pricing":{"name":"Provider source","url":"https://mi.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mi.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-opus-latest","slug":"anthropic-claude-opus-latest","canonicalId":"anthropic-claude-opus-latest","name":"Claude Opus Latest","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"~anthropic/claude-opus-latest","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000004,"completion":0.00002},"inputPrice":4,"outputPrice":20,"cachedInputPrice":null,"price":"$4.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":250,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-opus-latest","name":"Claude Opus Latest","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"~anthropic/claude-opus-latest","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":4,"outputPrice":20,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-4-image-2","slug":"openai-gpt-5-4-image-2","canonicalId":"openai-gpt-5-4-image-2","name":"GPT-5.4 Image 2","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.4-image-2-20260421","modalities":["Image","Text","File","Reasoning"],"context_length":"272000","context":"272000","contextWindow":"272000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000008,"completion":0.000015},"inputPrice":8,"outputPrice":15,"cachedInputPrice":null,"price":"$8.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.4-image-2","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.4-image-2","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":251,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-4-image-2","name":"GPT-5.4 Image 2","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.4-image-2-20260421","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Image","Text","File","Reasoning"],"contextWindow":"272000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":8,"outputPrice":15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openrouter-pareto-code","slug":"openrouter-pareto-code","canonicalId":"openrouter-pareto-code","name":"Pareto Code Router","provider":"OpenRouter","family":null,"status":"active","variantType":"router","modelVersion":"openrouter/pareto-code","modalities":["Text","Tools"],"context_length":"2000000","context":"2000000","contextWindow":"2000000","maxOutputTokens":null,"apiAvailable":true,"pricing":{"prompt":null,"completion":null},"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"price":"N/A","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":null,"catalogRank":252,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openrouter-pareto-code","name":"Pareto Code Router","provider":"OpenRouter","family":null,"status":"active","variantType":"router","modelVersion":"openrouter/pareto-code","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Tools"],"contextWindow":"2000000","maxOutputTokens":null,"apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-opus-4-7-batch","slug":"anthropic-claude-opus-4-7-batch","canonicalId":"anthropic-claude-opus-4-7-batch","name":"Claude Opus 4.7 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-4.7-opus-20260416","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.0000125},"inputPrice":2.5,"outputPrice":12.5,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":40.7,"coding":73.6,"agents":38.6,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":253,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-opus-4-7-batch","name":"Claude Opus 4.7 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-4.7-opus-20260416","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2.5,"outputPrice":12.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-5-1","slug":"z-ai-glm-5-1","canonicalId":"z-ai-glm-5-1","name":"GLM 5.1","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-5.1-20260406","modalities":["Text","Tools","Reasoning"],"context_length":"204800","context":"204800","contextWindow":"204800","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":0.00000133,"completion":0.00000418},"inputPrice":1.33,"outputPrice":4.18,"cachedInputPrice":null,"price":"$1.33","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":26.1,"coding":55.8,"agents":23.9,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":254,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-5-1","name":"GLM 5.1","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-5.1-20260406","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"204800","maxOutputTokens":"131072","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.33,"outputPrice":4.18,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemma-4-26b-a4b-it","slug":"google-gemma-4-26b-a4b-it","canonicalId":"google-gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemma-4-26b-a4b-it-20260403","modalities":["Image","Text","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":7.65e-8,"completion":2.55e-7},"inputPrice":0.0765,"outputPrice":0.255,"cachedInputPrice":null,"price":"$0.08","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":16.7,"coding":39.3,"agents":2.9,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":255,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemma-4-26b-a4b-it-20260403","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Image","Text","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.0765,"outputPrice":0.255,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemma-4-26b-a4b-it-free","slug":"google-gemma-4-26b-a4b-it-free","canonicalId":"google-gemma-4-26b-a4b-it-free","name":"Gemma 4 26B A4B (free)","provider":"Google","family":null,"status":"active","variantType":"free","modelVersion":"google/gemma-4-26b-a4b-it-20260403","modalities":["Image","Text","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":16.7,"coding":39.3,"agents":2.9,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":256,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemma-4-26b-a4b-it-free","name":"Gemma 4 26B A4B (free)","provider":"Google","family":null,"status":"active","variantType":"free","modelVersion":"google/gemma-4-26b-a4b-it-20260403","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Image","Text","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemma-4-31b-it","slug":"google-gemma-4-31b-it","canonicalId":"google-gemma-4-31b-it","name":"Gemma 4 31B","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemma-4-31b-it-20260402","modalities":["Image","Text","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":9e-8,"completion":3.4e-7},"inputPrice":0.09,"outputPrice":0.33999999999999997,"cachedInputPrice":null,"price":"$0.09","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":14.7,"coding":43.4,"agents":4.2,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":257,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemma-4-31b-it","name":"Gemma 4 31B","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemma-4-31b-it-20260402","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Image","Text","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.09,"outputPrice":0.33999999999999997,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemma-4-31b-it-batch","slug":"google-gemma-4-31b-it-batch","canonicalId":"google-gemma-4-31b-it-batch","name":"Gemma 4 31B (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemma-4-31b-it-20260402","modalities":["Image","Text","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":3.9e-7,"completion":9.7e-7},"inputPrice":0.39,"outputPrice":0.9700000000000001,"cachedInputPrice":null,"price":"$0.39","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":15.4,"coding":43.4,"agents":6.7,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-09-15","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":258,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemma-4-31b-it-batch","name":"Gemma 4 31B (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemma-4-31b-it-20260402","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Image","Text","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.39,"outputPrice":0.9700000000000001,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemma-4-31b-it-free","slug":"google-gemma-4-31b-it-free","canonicalId":"google-gemma-4-31b-it-free","name":"Gemma 4 31B (free)","provider":"Google","family":null,"status":"active","variantType":"free","modelVersion":"google/gemma-4-31b-it-20260402","modalities":["Image","Text","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":14.7,"coding":43.4,"agents":4.2,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":259,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemma-4-31b-it-free","name":"Gemma 4 31B (free)","provider":"Google","family":null,"status":"active","variantType":"free","modelVersion":"google/gemma-4-31b-it-20260402","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Image","Text","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-6-plus","slug":"qwen-qwen3-6-plus","canonicalId":"qwen-qwen3-6-plus","name":"Qwen3.6 Plus","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.6-plus-04-02","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":3.25e-7,"completion":0.00000195},"inputPrice":0.325,"outputPrice":1.95,"cachedInputPrice":null,"price":"$0.33","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":27,"coding":54.5,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":260,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-6-plus","name":"Qwen3.6 Plus","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.6-plus-04-02","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.325,"outputPrice":1.95,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"arcee-ai-trinity-large-thinking","slug":"arcee-ai-trinity-large-thinking","canonicalId":"arcee-ai-trinity-large-thinking","name":"Trinity Large Thinking","provider":"Arcee AI","family":null,"status":"active","variantType":"base","modelVersion":"arcee-ai/trinity-large-thinking","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"80000","apiAvailable":true,"pricing":{"prompt":2.5e-7,"completion":8e-7},"inputPrice":0.25,"outputPrice":0.7999999999999999,"cachedInputPrice":null,"price":"$0.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":10.8,"coding":25.8,"agents":1,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://arcee.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://arcee.ai/"},"pricing":{"name":"Provider source","url":"https://arcee.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://arcee.ai/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://arcee.ai/","sourceUrl":"https://arcee.ai/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=arcee.ai&sz=64","catalogRank":261,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"arcee-ai-trinity-large-thinking","name":"Trinity Large Thinking","provider":"Arcee AI","family":null,"status":"active","variantType":"base","modelVersion":"arcee-ai/trinity-large-thinking","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"80000","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.25,"outputPrice":0.7999999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://arcee.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://arcee.ai/"},"pricing":{"name":"Provider source","url":"https://arcee.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://arcee.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-5v-turbo","slug":"z-ai-glm-5v-turbo","canonicalId":"z-ai-glm-5v-turbo","name":"GLM 5V Turbo","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-5v-turbo-20260401","modalities":["Image","Text","Video","Tools","Reasoning"],"context_length":"202752","context":"202752","contextWindow":"202752","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":0.0000012,"completion":0.000004},"inputPrice":1.2,"outputPrice":4,"cachedInputPrice":null,"price":"$1.20","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":23.5,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":262,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-5v-turbo","name":"GLM 5V Turbo","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-5v-turbo-20260401","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Image","Text","Video","Tools","Reasoning"],"contextWindow":"202752","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.2,"outputPrice":4,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"x-ai-grok-4-20","slug":"x-ai-grok-4-20","canonicalId":"x-ai-grok-4-20","name":"Grok 4.20","provider":"xAI","family":null,"status":"active","variantType":"base","modelVersion":"x-ai/grok-4.20-20260309","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"2000000","context":"2000000","contextWindow":"2000000","maxOutputTokens":"1800000","apiAvailable":true,"pricing":{"prompt":0.00000125,"completion":0.0000025},"inputPrice":1.25,"outputPrice":2.5,"cachedInputPrice":null,"price":"$1.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":25.7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://x.ai/"},"pricing":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://x.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.x.ai/docs/models","catalogSourceUrl":"https://x.ai/","sourceUrl":"https://docs.x.ai/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=x.ai&sz=64","catalogRank":263,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"x-ai-grok-4-20","name":"Grok 4.20","provider":"xAI","family":null,"status":"active","variantType":"base","modelVersion":"x-ai/grok-4.20-20260309","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"2000000","maxOutputTokens":"1800000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.25,"outputPrice":2.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://x.ai/"},"pricing":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://x.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"x-ai-grok-4-20-multi-agent","slug":"x-ai-grok-4-20-multi-agent","canonicalId":"x-ai-grok-4-20-multi-agent","name":"Grok 4.20 Multi-Agent","provider":"xAI","family":null,"status":"active","variantType":"base","modelVersion":"x-ai/grok-4.20-multi-agent-20260309","modalities":["Text","Image","File","Reasoning"],"context_length":"2000000","context":"2000000","contextWindow":"2000000","maxOutputTokens":"1800000","apiAvailable":true,"pricing":{"prompt":0.00000125,"completion":0.0000025},"inputPrice":1.25,"outputPrice":2.5,"cachedInputPrice":null,"price":"$1.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://x.ai/"},"pricing":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://x.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.x.ai/docs/models","catalogSourceUrl":"https://x.ai/","sourceUrl":"https://docs.x.ai/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=x.ai&sz=64","catalogRank":264,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"x-ai-grok-4-20-multi-agent","name":"Grok 4.20 Multi-Agent","provider":"xAI","family":null,"status":"active","variantType":"base","modelVersion":"x-ai/grok-4.20-multi-agent-20260309","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Reasoning"],"contextWindow":"2000000","maxOutputTokens":"1800000","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.25,"outputPrice":2.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://x.ai/"},"pricing":{"name":"Provider source","url":"https://x.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://x.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-lyria-3-clip-preview","slug":"google-lyria-3-clip-preview","canonicalId":"google-lyria-3-clip-preview","name":"Lyria 3 Clip Preview","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/lyria-3-clip-preview-20260330","modalities":["Text","Image"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":265,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-lyria-3-clip-preview","name":"Lyria 3 Clip Preview","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/lyria-3-clip-preview-20260330","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-lyria-3-pro-preview","slug":"google-lyria-3-pro-preview","canonicalId":"google-lyria-3-pro-preview","name":"Lyria 3 Pro Preview","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/lyria-3-pro-preview-20260330","modalities":["Text","Image"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":266,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-lyria-3-pro-preview","name":"Lyria 3 Pro Preview","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/lyria-3-pro-preview-20260330","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"kwaipilot-kat-coder-pro-v2","slug":"kwaipilot-kat-coder-pro-v2","canonicalId":"kwaipilot-kat-coder-pro-v2","name":"KAT-Coder-Pro V2","provider":"KwaiPilot","family":null,"status":"active","variantType":"base","modelVersion":"kwaipilot/kat-coder-pro-v2-20260327","modalities":["Text","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"144000","apiAvailable":true,"pricing":{"prompt":3e-7,"completion":0.0000012},"inputPrice":0.3,"outputPrice":1.2,"cachedInputPrice":null,"price":"$0.30","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":0,"coding":59.5,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-09-22","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":null,"catalogRank":267,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"kwaipilot-kat-coder-pro-v2","name":"KAT-Coder-Pro V2","provider":"KwaiPilot","family":null,"status":"active","variantType":"base","modelVersion":"kwaipilot/kat-coder-pro-v2-20260327","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Tools"],"contextWindow":"262144","maxOutputTokens":"144000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.3,"outputPrice":1.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"rekaai-reka-edge","slug":"rekaai-reka-edge","canonicalId":"rekaai-reka-edge","name":"Reka Edge","provider":"Rekaai","family":null,"status":"active","variantType":"base","modelVersion":"rekaai/reka-edge-2603","modalities":["Image","Text","Video","Tools","Reasoning"],"context_length":"16384","context":"16384","contextWindow":"16384","maxOutputTokens":"14745","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":1e-7},"inputPrice":0.09999999999999999,"outputPrice":0.09999999999999999,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://reka.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://reka.ai/"},"pricing":{"name":"Provider source","url":"https://reka.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://reka.ai/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://reka.ai/","sourceUrl":"https://reka.ai/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=reka.ai&sz=64","catalogRank":268,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"rekaai-reka-edge","name":"Reka Edge","provider":"Rekaai","family":null,"status":"active","variantType":"base","modelVersion":"rekaai/reka-edge-2603","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Image","Text","Video","Tools","Reasoning"],"contextWindow":"16384","maxOutputTokens":"14745","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.09999999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://reka.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://reka.ai/"},"pricing":{"name":"Provider source","url":"https://reka.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://reka.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"minimax-minimax-m2-7","slug":"minimax-minimax-m2-7","canonicalId":"minimax-minimax-m2-7","name":"MiniMax M2.7","provider":"MiniMax","family":null,"status":"active","variantType":"base","modelVersion":"minimax/minimax-m2.7-20260318","modalities":["Text","Tools","Reasoning"],"context_length":"204800","context":"204800","contextWindow":"204800","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":3e-7,"completion":0.0000012},"inputPrice":0.3,"outputPrice":1.2,"cachedInputPrice":null,"price":"$0.30","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":22.8,"coding":52.6,"agents":15.3,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}},"officialUrl":"https://platform.minimax.io/docs/guides/models","catalogSourceUrl":"https://minimax.io/","sourceUrl":"https://platform.minimax.io/docs/guides/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=minimax.io&sz=64","catalogRank":269,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"minimax-minimax-m2-7","name":"MiniMax M2.7","provider":"MiniMax","family":null,"status":"active","variantType":"base","modelVersion":"minimax/minimax-m2.7-20260318","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"204800","maxOutputTokens":"131072","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.3,"outputPrice":1.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"minimax-minimax-m2-7-free","slug":"minimax-minimax-m2-7-free","canonicalId":"minimax-minimax-m2-7-free","name":"MiniMax M2.7 (free)","provider":"MiniMax","family":null,"status":"active","variantType":"free","modelVersion":"minimax/minimax-m2.7-20260318","modalities":["Text","Tools","Reasoning"],"context_length":"196608","context":"196608","contextWindow":"196608","maxOutputTokens":"176947","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":0,"coding":52.6,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}},"officialUrl":"https://platform.minimax.io/docs/guides/models","catalogSourceUrl":"https://minimax.io/","sourceUrl":"https://platform.minimax.io/docs/guides/models","sourceUpdatedAt":{},"updated":"2026-09-07","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=minimax.io&sz=64","catalogRank":270,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"minimax-minimax-m2-7-free","name":"MiniMax M2.7 (free)","provider":"MiniMax","family":null,"status":"active","variantType":"free","modelVersion":"minimax/minimax-m2.7-20260318","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"196608","maxOutputTokens":"176947","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-4-mini","slug":"openai-gpt-5-4-mini","canonicalId":"openai-gpt-5-4-mini","name":"GPT-5.4 Mini","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/gpt-5.4-mini-20260317","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":7.5e-7,"completion":0.0000045},"inputPrice":0.75,"outputPrice":4.5,"cachedInputPrice":null,"price":"$0.75","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":24.1,"coding":56.1,"agents":17.9,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.4-mini","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.4-mini","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":271,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-4-mini","name":"GPT-5.4 Mini","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/gpt-5.4-mini-20260317","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.75,"outputPrice":4.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-4-mini-batch","slug":"openai-gpt-5-4-mini-batch","canonicalId":"openai-gpt-5-4-mini-batch","name":"GPT-5.4 Mini (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.4-mini-20260317","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":3.75e-7,"completion":0.00000225},"inputPrice":0.375,"outputPrice":2.25,"cachedInputPrice":null,"price":"$0.38","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":24.1,"coding":56.1,"agents":17.9,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.4-mini:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.4-mini:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":272,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-4-mini-batch","name":"GPT-5.4 Mini (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.4-mini-20260317","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.375,"outputPrice":2.25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-4-nano","slug":"openai-gpt-5-4-nano","canonicalId":"openai-gpt-5-4-nano","name":"GPT-5.4 Nano","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.4-nano-20260317","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":2e-7,"completion":0.00000125},"inputPrice":0.19999999999999998,"outputPrice":1.25,"cachedInputPrice":null,"price":"$0.20","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":20.7,"coding":56.1,"agents":16,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.4-nano","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.4-nano","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":273,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-4-nano","name":"GPT-5.4 Nano","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.4-nano-20260317","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.19999999999999998,"outputPrice":1.25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-4-nano-batch","slug":"openai-gpt-5-4-nano-batch","canonicalId":"openai-gpt-5-4-nano-batch","name":"GPT-5.4 Nano (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.4-nano-20260317","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":6.25e-7},"inputPrice":0.09999999999999999,"outputPrice":0.625,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":20.7,"coding":56.1,"agents":16,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.4-nano:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.4-nano:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":274,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-4-nano-batch","name":"GPT-5.4 Nano (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.4-nano-20260317","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.625,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-mistral-small-2603","slug":"mistralai-mistral-small-2603","canonicalId":"mistralai-mistral-small-2603","name":"Mistral Small 4","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-small-2603","modalities":["Text","Image","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"pricing":{"prompt":1.5e-7,"completion":6e-7},"inputPrice":0.15,"outputPrice":0.6,"cachedInputPrice":null,"price":"$0.15","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":11.3,"coding":26.6,"agents":0.8,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":275,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-mistral-small-2603","name":"Mistral Small 4","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-small-2603","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.15,"outputPrice":0.6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-mistral-small-2603-batch","slug":"mistralai-mistral-small-2603-batch","canonicalId":"mistralai-mistral-small-2603-batch","name":"Mistral Small 4 (batch)","provider":"Mistral","family":null,"status":"active","variantType":"batch","modelVersion":"mistralai/mistral-small-2603","modalities":["Text","Image","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"pricing":{"prompt":7.5e-8,"completion":3e-7},"inputPrice":0.075,"outputPrice":0.3,"cachedInputPrice":null,"price":"$0.07","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":11.3,"coding":26.6,"agents":0.8,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":276,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-mistral-small-2603-batch","name":"Mistral Small 4 (batch)","provider":"Mistral","family":null,"status":"active","variantType":"batch","modelVersion":"mistralai/mistral-small-2603","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.075,"outputPrice":0.3,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-5-turbo","slug":"z-ai-glm-5-turbo","canonicalId":"z-ai-glm-5-turbo","name":"GLM 5 Turbo","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-5-turbo-20260315","modalities":["Text","Tools","Reasoning"],"context_length":"202752","context":"202752","contextWindow":"202752","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":0.0000012,"completion":0.000004},"inputPrice":1.2,"outputPrice":4,"cachedInputPrice":null,"price":"$1.20","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":26.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":277,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-5-turbo","name":"GLM 5 Turbo","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-5-turbo-20260315","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Tools","Reasoning"],"contextWindow":"202752","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.2,"outputPrice":4,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"nvidia-nemotron-3-super-120b-a12b","slug":"nvidia-nemotron-3-super-120b-a12b","canonicalId":"nvidia-nemotron-3-super-120b-a12b","name":"Nemotron 3 Super","provider":"NVIDIA","family":null,"status":"active","variantType":"base","modelVersion":"nvidia/nemotron-3-super-120b-a12b-20230311","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":8e-8,"completion":4.5e-7},"inputPrice":0.08,"outputPrice":0.44999999999999996,"cachedInputPrice":null,"price":"$0.08","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":12.8,"coding":37.7,"agents":1.7,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}},"officialUrl":"https://build.nvidia.com/explore/discover","catalogSourceUrl":"https://nvidia.com/","sourceUrl":"https://build.nvidia.com/explore/discover","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=nvidia.com&sz=64","catalogRank":278,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"nvidia-nemotron-3-super-120b-a12b","name":"Nemotron 3 Super","provider":"NVIDIA","family":null,"status":"active","variantType":"base","modelVersion":"nvidia/nemotron-3-super-120b-a12b-20230311","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.08,"outputPrice":0.44999999999999996,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"nvidia-nemotron-3-super-120b-a12b-free","slug":"nvidia-nemotron-3-super-120b-a12b-free","canonicalId":"nvidia-nemotron-3-super-120b-a12b-free","name":"Nemotron 3 Super (free)","provider":"NVIDIA","family":null,"status":"active","variantType":"free","modelVersion":"nvidia/nemotron-3-super-120b-a12b-20230311","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":12.8,"coding":37.7,"agents":1.7,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}},"officialUrl":"https://build.nvidia.com/explore/discover","catalogSourceUrl":"https://nvidia.com/","sourceUrl":"https://build.nvidia.com/explore/discover","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=nvidia.com&sz=64","catalogRank":279,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"nvidia-nemotron-3-super-120b-a12b-free","name":"Nemotron 3 Super (free)","provider":"NVIDIA","family":null,"status":"active","variantType":"free","modelVersion":"nvidia/nemotron-3-super-120b-a12b-20230311","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"bytedance-seed-seed-2-0-lite","slug":"bytedance-seed-seed-2-0-lite","canonicalId":"bytedance-seed-seed-2-0-lite","name":"Seed-2.0-Lite","provider":"ByteDance Seed","family":null,"status":"active","variantType":"fast","modelVersion":"bytedance-seed/seed-2.0-lite-20260309","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":2.5e-7,"completion":0.000002},"inputPrice":0.25,"outputPrice":2,"cachedInputPrice":null,"price":"$0.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"pricing":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"metrics":{},"fields":{}},"officialUrl":"https://seed.bytedance.com/en/seed2_1","catalogSourceUrl":"https://seed.bytedance.com/","sourceUrl":"https://seed.bytedance.com/en/seed2_1","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=seed.bytedance.com&sz=64","catalogRank":280,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"bytedance-seed-seed-2-0-lite","name":"Seed-2.0-Lite","provider":"ByteDance Seed","family":null,"status":"active","variantType":"fast","modelVersion":"bytedance-seed/seed-2.0-lite-20260309","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.25,"outputPrice":2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"pricing":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-5-9b","slug":"qwen-qwen3-5-9b","canonicalId":"qwen-qwen3-5-9b","name":"Qwen3.5-9B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.5-9b-20260310","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":1.5e-7},"inputPrice":0.09999999999999999,"outputPrice":0.15,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":13.3,"coding":23.5,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":281,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-5-9b","name":"Qwen3.5-9B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.5-9b-20260310","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-5-9b-batch","slug":"qwen-qwen3-5-9b-batch","canonicalId":"qwen-qwen3-5-9b-batch","name":"Qwen3.5-9B (batch)","provider":"Qwen","family":null,"status":"active","variantType":"batch","modelVersion":"qwen/qwen3.5-9b-20260310","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":1.7e-7,"completion":2.5e-7},"inputPrice":0.16999999999999998,"outputPrice":0.25,"cachedInputPrice":null,"price":"$0.17","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":0,"coding":28.7,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-09-21","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":282,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-5-9b-batch","name":"Qwen3.5-9B (batch)","provider":"Qwen","family":null,"status":"active","variantType":"batch","modelVersion":"qwen/qwen3.5-9b-20260310","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.16999999999999998,"outputPrice":0.25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-4","slug":"openai-gpt-5-4","canonicalId":"openai-gpt-5-4","name":"GPT-5.4","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.4-20260305","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.000015},"inputPrice":2.5,"outputPrice":15,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":39,"coding":71.1,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.4","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.4","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":283,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-4","name":"GPT-5.4","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.4-20260305","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2.5,"outputPrice":15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-4-batch","slug":"openai-gpt-5-4-batch","canonicalId":"openai-gpt-5-4-batch","name":"GPT-5.4 (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.4-20260305","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00000125,"completion":0.0000075},"inputPrice":1.25,"outputPrice":7.5,"cachedInputPrice":null,"price":"$1.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":39,"coding":71.1,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.4:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.4:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":284,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-4-batch","name":"GPT-5.4 (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.4-20260305","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.25,"outputPrice":7.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-4-pro","slug":"openai-gpt-5-4-pro","canonicalId":"openai-gpt-5-4-pro","name":"GPT-5.4 Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.4-pro-20260305","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00003,"completion":0.00018},"inputPrice":30,"outputPrice":180,"cachedInputPrice":null,"price":"$30.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.4-pro","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.4-pro","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":285,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-4-pro","name":"GPT-5.4 Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.4-pro-20260305","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":30,"outputPrice":180,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-4-pro-batch","slug":"openai-gpt-5-4-pro-batch","canonicalId":"openai-gpt-5-4-pro-batch","name":"GPT-5.4 Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.4-pro-20260305","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1050000","context":"1050000","contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000015,"completion":0.00009},"inputPrice":15,"outputPrice":90,"cachedInputPrice":null,"price":"$15.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.4-pro:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.4-pro:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":286,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-4-pro-batch","name":"GPT-5.4 Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.4-pro-20260305","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1050000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":15,"outputPrice":90,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"inception-mercury-2","slug":"inception-mercury-2","canonicalId":"inception-mercury-2","name":"Mercury 2","provider":"Inception","family":null,"status":"active","variantType":"base","modelVersion":"inception/mercury-2-20260304","modalities":["Text","Tools","Reasoning"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"50000","apiAvailable":true,"pricing":{"prompt":2.5e-7,"completion":7.5e-7},"inputPrice":0.25,"outputPrice":0.75,"cachedInputPrice":null,"price":"$0.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":13.8,"coding":31.1,"agents":1.6,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":null,"catalogRank":287,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"inception-mercury-2","name":"Mercury 2","provider":"Inception","family":null,"status":"active","variantType":"base","modelVersion":"inception/mercury-2-20260304","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Tools","Reasoning"],"contextWindow":"128000","maxOutputTokens":"50000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.25,"outputPrice":0.75,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-1-flash-lite-preview","slug":"google-gemini-3-1-flash-lite-preview","canonicalId":"google-gemini-3-1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/gemini-3.1-flash-lite-preview-20260303","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":2.5e-7,"completion":0.0000015},"inputPrice":0.25,"outputPrice":1.5,"cachedInputPrice":null,"price":"$0.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":15.6,"coding":34.7,"agents":1.6,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":288,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/gemini-3.1-flash-lite-preview-20260303","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","File","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.25,"outputPrice":1.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"bytedance-seed-seed-2-0-mini","slug":"bytedance-seed-seed-2-0-mini","canonicalId":"bytedance-seed-seed-2-0-mini","name":"Seed-2.0-Mini","provider":"ByteDance Seed","family":null,"status":"active","variantType":"fast","modelVersion":"bytedance-seed/seed-2.0-mini-20260224","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":4e-7},"inputPrice":0.09999999999999999,"outputPrice":0.39999999999999997,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"pricing":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"metrics":{},"fields":{}},"officialUrl":"https://seed.bytedance.com/en/seed2_1","catalogSourceUrl":"https://seed.bytedance.com/","sourceUrl":"https://seed.bytedance.com/en/seed2_1","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=seed.bytedance.com&sz=64","catalogRank":289,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"bytedance-seed-seed-2-0-mini","name":"Seed-2.0-Mini","provider":"ByteDance Seed","family":null,"status":"active","variantType":"fast","modelVersion":"bytedance-seed/seed-2.0-mini-20260224","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.39999999999999997,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"pricing":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-1-flash-image-preview","slug":"google-gemini-3-1-flash-image-preview","canonicalId":"google-gemini-3-1-flash-image-preview","name":"Nano Banana 2 (Gemini 3.1 Flash Image Preview)","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/gemini-3.1-flash-image-preview-20260226","modalities":["Image","Text","Reasoning"],"context_length":"65536","context":"65536","contextWindow":"65536","maxOutputTokens":"58982","apiAvailable":true,"pricing":{"prompt":5e-7,"completion":0.000003},"inputPrice":0.5,"outputPrice":3,"cachedInputPrice":null,"price":"$0.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":290,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-1-flash-image-preview","name":"Nano Banana 2 (Gemini 3.1 Flash Image Preview)","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/gemini-3.1-flash-image-preview-20260226","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Image","Text","Reasoning"],"contextWindow":"65536","maxOutputTokens":"58982","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.5,"outputPrice":3,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-1-pro-preview-customtools","slug":"google-gemini-3-1-pro-preview-customtools","canonicalId":"google-gemini-3-1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/gemini-3.1-pro-preview-customtools-20260219","modalities":["Text","Audio","Image","Video","File","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000012},"inputPrice":2,"outputPrice":12,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":291,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/gemini-3.1-pro-preview-customtools-20260219","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Audio","Image","Video","File","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":12,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-5-122b-a10b","slug":"qwen-qwen3-5-122b-a10b","canonicalId":"qwen-qwen3-5-122b-a10b","name":"Qwen3.5-122B-A10B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.5-122b-a10b-20260224","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":2.6e-7,"completion":0.00000208},"inputPrice":0.26,"outputPrice":2.08,"cachedInputPrice":null,"price":"$0.26","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":17.7,"coding":43.3,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":292,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-5-122b-a10b","name":"Qwen3.5-122B-A10B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.5-122b-a10b-20260224","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"65536","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.26,"outputPrice":2.08,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-5-27b","slug":"qwen-qwen3-5-27b","canonicalId":"qwen-qwen3-5-27b","name":"Qwen3.5-27B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.5-27b-20260224","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"81920","apiAvailable":true,"pricing":{"prompt":2.6e-7,"completion":0.0000026},"inputPrice":0.26,"outputPrice":2.6,"cachedInputPrice":null,"price":"$0.26","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":22.9,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":293,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-5-27b","name":"Qwen3.5-27B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.5-27b-20260224","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"81920","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.26,"outputPrice":2.6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-5-35b-a3b","slug":"qwen-qwen3-5-35b-a3b","canonicalId":"qwen-qwen3-5-35b-a3b","name":"Qwen3.5-35B-A3B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.5-35b-a3b-20260224","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":1.5e-7,"completion":0.000001},"inputPrice":0.15,"outputPrice":1,"cachedInputPrice":null,"price":"$0.15","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":19.3,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":294,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-5-35b-a3b","name":"Qwen3.5-35B-A3B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.5-35b-a3b-20260224","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.15,"outputPrice":1,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-5-flash-02-23","slug":"qwen-qwen3-5-flash-02-23","canonicalId":"qwen-qwen3-5-flash-02-23","name":"Qwen3.5-Flash","provider":"Qwen","family":null,"status":"active","variantType":"fast","modelVersion":"qwen/qwen3.5-flash-20260224","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":6.5e-8,"completion":2.6e-7},"inputPrice":0.065,"outputPrice":0.26,"cachedInputPrice":null,"price":"$0.07","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":295,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-5-flash-02-23","name":"Qwen3.5-Flash","provider":"Qwen","family":null,"status":"active","variantType":"fast","modelVersion":"qwen/qwen3.5-flash-20260224","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.065,"outputPrice":0.26,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-3-codex","slug":"openai-gpt-5-3-codex","canonicalId":"openai-gpt-5-3-codex","name":"GPT-5.3-Codex","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.3-codex-20260224","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00000175,"completion":0.000014},"inputPrice":1.75,"outputPrice":14,"cachedInputPrice":null,"price":"$1.75","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":32.5,"coding":0,"agents":0,"speed":null,"latency":3,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.3-codex","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.3-codex","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":296,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-3-codex","name":"GPT-5.3-Codex","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.3-codex-20260224","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.75,"outputPrice":14,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"aion-labs-aion-2-0","slug":"aion-labs-aion-2-0","canonicalId":"aion-labs-aion-2-0","name":"Aion-2.0","provider":"AionLabs","family":null,"status":"active","variantType":"base","modelVersion":"aion-labs/aion-2.0-20260223","modalities":["Text","Tools","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":8e-7,"completion":0.0000016},"inputPrice":0.7999999999999999,"outputPrice":1.5999999999999999,"cachedInputPrice":null,"price":"$0.80","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aionlabs.ai/"},"pricing":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aionlabs.ai/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://aionlabs.ai/","sourceUrl":"https://aionlabs.ai/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=aionlabs.ai&sz=64","catalogRank":297,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"aion-labs-aion-2-0","name":"Aion-2.0","provider":"AionLabs","family":null,"status":"active","variantType":"base","modelVersion":"aion-labs/aion-2.0-20260223","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Tools","Reasoning"],"contextWindow":"131072","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.7999999999999999,"outputPrice":1.5999999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aionlabs.ai/"},"pricing":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aionlabs.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-1-pro-preview","slug":"google-gemini-3-1-pro-preview","canonicalId":"google-gemini-3-1-pro-preview","name":"Gemini 3.1 Pro Preview","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/gemini-3.1-pro-preview-20260219","modalities":["Audio","File","Image","Text","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000012},"inputPrice":2,"outputPrice":12,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":29.7,"coding":68.8,"agents":8.2,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":298,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-1-pro-preview","name":"Gemini 3.1 Pro Preview","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/gemini-3.1-pro-preview-20260219","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Audio","File","Image","Text","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":12,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-1-pro-preview-batch","slug":"google-gemini-3-1-pro-preview-batch","canonicalId":"google-gemini-3-1-pro-preview-batch","name":"Gemini 3.1 Pro Preview (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-3.1-pro-preview-20260219","modalities":["Audio","File","Image","Text","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000006},"inputPrice":1,"outputPrice":6,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":29.7,"coding":68.8,"agents":8.2,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":299,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-1-pro-preview-batch","name":"Gemini 3.1 Pro Preview (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-3.1-pro-preview-20260219","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Audio","File","Image","Text","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":1,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-sonnet-4-6-batch","slug":"anthropic-claude-sonnet-4-6-batch","canonicalId":"anthropic-claude-sonnet-4-6-batch","name":"Claude Sonnet 4.6 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-4.6-sonnet-20260217","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.0000015,"completion":0.0000075},"inputPrice":1.5,"outputPrice":7.5,"cachedInputPrice":null,"price":"$1.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":30.1,"coding":63,"agents":31.8,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":300,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-sonnet-4-6-batch","name":"Claude Sonnet 4.6 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-4.6-sonnet-20260217","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.5,"outputPrice":7.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-5-397b-a17b","slug":"qwen-qwen3-5-397b-a17b","canonicalId":"qwen-qwen3-5-397b-a17b","name":"Qwen3.5 397B A17B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.5-397b-a17b-20260216","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":5e-7,"completion":0.0000036},"inputPrice":0.5,"outputPrice":3.5999999999999996,"cachedInputPrice":null,"price":"$0.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":21.4,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":301,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-5-397b-a17b","name":"Qwen3.5 397B A17B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3.5-397b-a17b-20260216","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.5,"outputPrice":3.5999999999999996,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-5-plus-02-15","slug":"qwen-qwen3-5-plus-02-15","canonicalId":"qwen-qwen3-5-plus-02-15","name":"Qwen3.5 Plus 2026-02-15","provider":"Qwen","family":null,"status":"active","variantType":"dated","modelVersion":"qwen/qwen3.5-plus-20260216","modalities":["Text","Image","Video","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":2.6e-7,"completion":0.00000156},"inputPrice":0.26,"outputPrice":1.56,"cachedInputPrice":null,"price":"$0.26","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":302,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-5-plus-02-15","name":"Qwen3.5 Plus 2026-02-15","provider":"Qwen","family":null,"status":"active","variantType":"dated","modelVersion":"qwen/qwen3.5-plus-20260216","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.26,"outputPrice":1.56,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"minimax-minimax-m2-5","slug":"minimax-minimax-m2-5","canonicalId":"minimax-minimax-m2-5","name":"MiniMax M2.5","provider":"MiniMax","family":null,"status":"active","variantType":"base","modelVersion":"minimax/minimax-m2.5-20260211","modalities":["Text","Tools","Reasoning"],"context_length":"204800","context":"204800","contextWindow":"204800","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":2.7e-7,"completion":0.00000108},"inputPrice":0.27,"outputPrice":1.08,"cachedInputPrice":null,"price":"$0.27","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":22.8,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}},"officialUrl":"https://platform.minimax.io/docs/guides/models","catalogSourceUrl":"https://minimax.io/","sourceUrl":"https://platform.minimax.io/docs/guides/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=minimax.io&sz=64","catalogRank":303,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"minimax-minimax-m2-5","name":"MiniMax M2.5","provider":"MiniMax","family":null,"status":"active","variantType":"base","modelVersion":"minimax/minimax-m2.5-20260211","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"204800","maxOutputTokens":"128000","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.27,"outputPrice":1.08,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-5","slug":"z-ai-glm-5","canonicalId":"z-ai-glm-5","name":"GLM 5","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-5-20260211","modalities":["Text","Tools","Reasoning"],"context_length":"204800","context":"204800","contextWindow":"204800","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":6e-7,"completion":0.00000192},"inputPrice":0.6,"outputPrice":1.92,"cachedInputPrice":null,"price":"$0.60","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":27.9,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":304,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-5","name":"GLM 5","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-5-20260211","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"204800","maxOutputTokens":"128000","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.6,"outputPrice":1.92,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-opus-4-6-batch","slug":"anthropic-claude-opus-4-6-batch","canonicalId":"anthropic-claude-opus-4-6-batch","name":"Claude Opus 4.6 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-4.6-opus-20260205","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.0000125},"inputPrice":2.5,"outputPrice":12.5,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":31.9,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":305,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-opus-4-6-batch","name":"Claude Opus 4.6 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-4.6-opus-20260205","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2.5,"outputPrice":12.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-coder-next","slug":"qwen-qwen3-coder-next","canonicalId":"qwen-qwen3-coder-next","name":"Qwen3 Coder Next","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-coder-next-2025-02-03","modalities":["Text","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":1.2e-7,"completion":8e-7},"inputPrice":0.12,"outputPrice":0.7999999999999999,"cachedInputPrice":null,"price":"$0.12","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":9.2,"coding":36.2,"agents":0.9,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":306,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-coder-next","name":"Qwen3 Coder Next","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-coder-next-2025-02-03","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.12,"outputPrice":0.7999999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openrouter-free","slug":"openrouter-free","canonicalId":"openrouter-free","name":"Free Models Router","provider":"OpenRouter","family":null,"status":"active","variantType":"free","modelVersion":"openrouter/free","modalities":["Text","Image","Tools"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":null,"apiAvailable":true,"pricing":{"prompt":0,"completion":0},"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"price":"$0.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":null,"catalogRank":307,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openrouter-free","name":"Free Models Router","provider":"OpenRouter","family":null,"status":"active","variantType":"free","modelVersion":"openrouter/free","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Tools"],"contextWindow":"200000","maxOutputTokens":null,"apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0,"outputPrice":0,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"stepfun-step-3-5-flash","slug":"stepfun-step-3-5-flash","canonicalId":"stepfun-step-3-5-flash","name":"Step 3.5 Flash","provider":"StepFun","family":null,"status":"active","variantType":"fast","modelVersion":"stepfun/step-3.5-flash","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":3e-7},"inputPrice":0.09999999999999999,"outputPrice":0.3,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":17,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://stepfun.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://stepfun.com/"},"pricing":{"name":"Provider source","url":"https://stepfun.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://stepfun.com/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://stepfun.com/","sourceUrl":"https://stepfun.com/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=stepfun.com&sz=64","catalogRank":308,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"stepfun-step-3-5-flash","name":"Step 3.5 Flash","provider":"StepFun","family":null,"status":"active","variantType":"fast","modelVersion":"stepfun/step-3.5-flash","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"65536","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.3,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://stepfun.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://stepfun.com/"},"pricing":{"name":"Provider source","url":"https://stepfun.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://stepfun.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"upstage-solar-pro-3","slug":"upstage-solar-pro-3","canonicalId":"upstage-solar-pro-3","name":"Solar Pro 3","provider":"Upstage","family":null,"status":"active","variantType":"base","modelVersion":"upstage/solar-pro-3","modalities":["Text","Tools","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"pricing":{"prompt":1.5e-7,"completion":6e-7},"inputPrice":0.15,"outputPrice":0.6,"cachedInputPrice":null,"price":"$0.15","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7.8,"coding":16.2,"agents":1.4,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://upstage.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://upstage.ai/"},"pricing":{"name":"Provider source","url":"https://upstage.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://upstage.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.upstage.ai/docs/apis/chat","catalogSourceUrl":"https://upstage.ai/","sourceUrl":"https://developers.upstage.ai/docs/apis/chat","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=upstage.ai&sz=64","catalogRank":309,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"upstage-solar-pro-3","name":"Solar Pro 3","provider":"Upstage","family":null,"status":"active","variantType":"base","modelVersion":"upstage/solar-pro-3","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Tools","Reasoning"],"contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.15,"outputPrice":0.6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://upstage.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://upstage.ai/"},"pricing":{"name":"Provider source","url":"https://upstage.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://upstage.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"minimax-minimax-m2-her","slug":"minimax-minimax-m2-her","canonicalId":"minimax-minimax-m2-her","name":"MiniMax M2-her","provider":"MiniMax","family":null,"status":"active","variantType":"base","modelVersion":"minimax/minimax-m2-her-20260123","modalities":["Text"],"context_length":"65536","context":"65536","contextWindow":"65536","maxOutputTokens":"2048","apiAvailable":true,"pricing":{"prompt":3e-7,"completion":0.0000012},"inputPrice":0.3,"outputPrice":1.2,"cachedInputPrice":null,"price":"$0.30","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}},"officialUrl":"https://platform.minimax.io/docs/guides/models","catalogSourceUrl":"https://minimax.io/","sourceUrl":"https://platform.minimax.io/docs/guides/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=minimax.io&sz=64","catalogRank":310,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"minimax-minimax-m2-her","name":"MiniMax M2-her","provider":"MiniMax","family":null,"status":"active","variantType":"base","modelVersion":"minimax/minimax-m2-her-20260123","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text"],"contextWindow":"65536","maxOutputTokens":"2048","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.3,"outputPrice":1.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"writer-palmyra-x5","slug":"writer-palmyra-x5","canonicalId":"writer-palmyra-x5","name":"Palmyra X5","provider":"Writer","family":null,"status":"active","variantType":"base","modelVersion":"writer/palmyra-x5-20250428","modalities":["Text"],"context_length":"1040000","context":"1040000","contextWindow":"1040000","maxOutputTokens":"8192","apiAvailable":true,"pricing":{"prompt":6e-7,"completion":0.000006},"inputPrice":0.6,"outputPrice":6,"cachedInputPrice":null,"price":"$0.60","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://writer.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://writer.com/"},"pricing":{"name":"Provider source","url":"https://writer.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://writer.com/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://writer.com/","sourceUrl":"https://writer.com/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=writer.com&sz=64","catalogRank":311,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"writer-palmyra-x5","name":"Palmyra X5","provider":"Writer","family":null,"status":"active","variantType":"base","modelVersion":"writer/palmyra-x5-20250428","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text"],"contextWindow":"1040000","maxOutputTokens":"8192","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.6,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://writer.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://writer.com/"},"pricing":{"name":"Provider source","url":"https://writer.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://writer.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-audio","slug":"openai-gpt-audio","canonicalId":"openai-gpt-audio","name":"GPT Audio","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-audio","modalities":["Text","Audio","Tools"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.00001},"inputPrice":2.5,"outputPrice":10,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-audio","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-audio","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":312,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-audio","name":"GPT Audio","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-audio","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Audio","Tools"],"contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":2.5,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-audio-mini","slug":"openai-gpt-audio-mini","canonicalId":"openai-gpt-audio-mini","name":"GPT Audio Mini","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/gpt-audio-mini","modalities":["Text","Audio","Tools"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":6e-7,"completion":0.0000024},"inputPrice":0.6,"outputPrice":2.4,"cachedInputPrice":null,"price":"$0.60","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-audio-mini","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-audio-mini","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":313,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-audio-mini","name":"GPT Audio Mini","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/gpt-audio-mini","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Audio","Tools"],"contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.6,"outputPrice":2.4,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-4-7-flash","slug":"z-ai-glm-4-7-flash","canonicalId":"z-ai-glm-4-7-flash","name":"GLM 4.7 Flash","provider":"Z.ai","family":null,"status":"active","variantType":"fast","modelVersion":"z-ai/glm-4.7-flash-20260119","modalities":["Text","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"117964","apiAvailable":true,"pricing":{"prompt":6.05e-8,"completion":4e-7},"inputPrice":0.060500000000000005,"outputPrice":0.39999999999999997,"cachedInputPrice":null,"price":"$0.06","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":14.9,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":314,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-4-7-flash","name":"GLM 4.7 Flash","provider":"Z.ai","family":null,"status":"active","variantType":"fast","modelVersion":"z-ai/glm-4.7-flash-20260119","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"117964","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.060500000000000005,"outputPrice":0.39999999999999997,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-2-codex","slug":"openai-gpt-5-2-codex","canonicalId":"openai-gpt-5-2-codex","name":"GPT-5.2-Codex","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.2-codex-20260114","modalities":["Text","Image","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00000175,"completion":0.000014},"inputPrice":1.75,"outputPrice":14,"cachedInputPrice":null,"price":"$1.75","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":28.5,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.2-codex","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.2-codex","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":315,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-2-codex","name":"GPT-5.2-Codex","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.2-codex-20260114","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.75,"outputPrice":14,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"bytedance-seed-seed-1-6","slug":"bytedance-seed-seed-1-6","canonicalId":"bytedance-seed-seed-1-6","name":"Seed 1.6","provider":"ByteDance Seed","family":null,"status":"active","variantType":"base","modelVersion":"bytedance-seed/seed-1.6-20250625","modalities":["Image","Text","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":2.5e-7,"completion":0.000002},"inputPrice":0.25,"outputPrice":2,"cachedInputPrice":null,"price":"$0.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"pricing":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"metrics":{},"fields":{}},"officialUrl":"https://seed.bytedance.com/en/seed2_1","catalogSourceUrl":"https://seed.bytedance.com/","sourceUrl":"https://seed.bytedance.com/en/seed2_1","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=seed.bytedance.com&sz=64","catalogRank":316,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"bytedance-seed-seed-1-6","name":"Seed 1.6","provider":"ByteDance Seed","family":null,"status":"active","variantType":"base","modelVersion":"bytedance-seed/seed-1.6-20250625","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Image","Text","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.25,"outputPrice":2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"pricing":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"bytedance-seed-seed-1-6-flash","slug":"bytedance-seed-seed-1-6-flash","canonicalId":"bytedance-seed-seed-1-6-flash","name":"Seed 1.6 Flash","provider":"ByteDance Seed","family":null,"status":"active","variantType":"fast","modelVersion":"bytedance-seed/seed-1.6-flash-20250625","modalities":["Image","Text","Video","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":7.5e-8,"completion":3e-7},"inputPrice":0.075,"outputPrice":0.3,"cachedInputPrice":null,"price":"$0.07","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"pricing":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"metrics":{},"fields":{}},"officialUrl":"https://seed.bytedance.com/en/seed2_1","catalogSourceUrl":"https://seed.bytedance.com/","sourceUrl":"https://seed.bytedance.com/en/seed2_1","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=seed.bytedance.com&sz=64","catalogRank":317,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"bytedance-seed-seed-1-6-flash","name":"Seed 1.6 Flash","provider":"ByteDance Seed","family":null,"status":"active","variantType":"fast","modelVersion":"bytedance-seed/seed-1.6-flash-20250625","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Image","Text","Video","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.075,"outputPrice":0.3,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"pricing":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"minimax-minimax-m2-1","slug":"minimax-minimax-m2-1","canonicalId":"minimax-minimax-m2-1","name":"MiniMax M2.1","provider":"MiniMax","family":null,"status":"active","variantType":"base","modelVersion":"minimax/minimax-m2.1","modalities":["Text","Tools","Reasoning"],"context_length":"204800","context":"204800","contextWindow":"204800","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":3e-7,"completion":0.0000012},"inputPrice":0.3,"outputPrice":1.2,"cachedInputPrice":null,"price":"$0.30","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":20.9,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}},"officialUrl":"https://platform.minimax.io/docs/guides/models","catalogSourceUrl":"https://minimax.io/","sourceUrl":"https://platform.minimax.io/docs/guides/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=minimax.io&sz=64","catalogRank":318,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"minimax-minimax-m2-1","name":"MiniMax M2.1","provider":"MiniMax","family":null,"status":"active","variantType":"base","modelVersion":"minimax/minimax-m2.1","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"204800","maxOutputTokens":"131072","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.3,"outputPrice":1.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-4-7","slug":"z-ai-glm-4-7","canonicalId":"z-ai-glm-4-7","name":"GLM 4.7","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-4.7-20251222","modalities":["Text","Tools","Reasoning"],"context_length":"204800","context":"204800","contextWindow":"204800","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":6e-7,"completion":0.0000022},"inputPrice":0.6,"outputPrice":2.2,"cachedInputPrice":null,"price":"$0.60","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":22.2,"coding":45.3,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":319,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-4-7","name":"GLM 4.7","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-4.7-20251222","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"204800","maxOutputTokens":"131072","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.6,"outputPrice":2.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-flash-preview","slug":"google-gemini-3-flash-preview","canonicalId":"google-gemini-3-flash-preview","name":"Gemini 3 Flash Preview","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/gemini-3-flash-preview-20251217","modalities":["Text","Image","File","Audio","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":5e-7,"completion":0.000003},"inputPrice":0.5,"outputPrice":3,"cachedInputPrice":null,"price":"$0.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":26.3,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":320,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-flash-preview","name":"Gemini 3 Flash Preview","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/gemini-3-flash-preview-20251217","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Audio","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.5,"outputPrice":3,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-flash-preview-batch","slug":"google-gemini-3-flash-preview-batch","canonicalId":"google-gemini-3-flash-preview-batch","name":"Gemini 3 Flash Preview (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-3-flash-preview-20251217","modalities":["Text","Image","File","Audio","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":2.5e-7,"completion":0.0000015},"inputPrice":0.25,"outputPrice":1.5,"cachedInputPrice":null,"price":"$0.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":26.3,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":321,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-flash-preview-batch","name":"Gemini 3 Flash Preview (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-3-flash-preview-20251217","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Audio","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.25,"outputPrice":1.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"nvidia-nemotron-3-nano-30b-a3b","slug":"nvidia-nemotron-3-nano-30b-a3b","canonicalId":"nvidia-nemotron-3-nano-30b-a3b","name":"Nemotron 3 Nano 30B A3B","provider":"NVIDIA","family":null,"status":"active","variantType":"base","modelVersion":"nvidia/nemotron-3-nano-30b-a3b","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":6e-8,"completion":2.4e-7},"inputPrice":0.06,"outputPrice":0.24,"cachedInputPrice":null,"price":"$0.06","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":8.9,"coding":14.4,"agents":1,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}},"officialUrl":"https://build.nvidia.com/explore/discover","catalogSourceUrl":"https://nvidia.com/","sourceUrl":"https://build.nvidia.com/explore/discover","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=nvidia.com&sz=64","catalogRank":322,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"nvidia-nemotron-3-nano-30b-a3b","name":"Nemotron 3 Nano 30B A3B","provider":"NVIDIA","family":null,"status":"active","variantType":"base","modelVersion":"nvidia/nemotron-3-nano-30b-a3b","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.06,"outputPrice":0.24,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://nvidia.com/"},"pricing":{"name":"Provider source","url":"https://nvidia.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://nvidia.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-2","slug":"openai-gpt-5-2","canonicalId":"openai-gpt-5-2","name":"GPT-5.2","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.2-20251211","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00000175,"completion":0.000014},"inputPrice":1.75,"outputPrice":14,"cachedInputPrice":null,"price":"$1.75","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":30.4,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.2","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.2","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":323,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-2","name":"GPT-5.2","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.2-20251211","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.75,"outputPrice":14,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-2-batch","slug":"openai-gpt-5-2-batch","canonicalId":"openai-gpt-5-2-batch","name":"GPT-5.2 (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.2-20251211","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":8.75e-7,"completion":0.000007},"inputPrice":0.875,"outputPrice":7,"cachedInputPrice":null,"price":"$0.88","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":30.4,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.2:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.2:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":324,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-2-batch","name":"GPT-5.2 (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.2-20251211","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.875,"outputPrice":7,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-2-chat","slug":"openai-gpt-5-2-chat","canonicalId":"openai-gpt-5-2-chat","name":"GPT-5.2 Chat","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.2-chat-20251211","modalities":["File","Image","Text","Tools"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"32000","apiAvailable":true,"pricing":{"prompt":0.00000175,"completion":0.000014},"inputPrice":1.75,"outputPrice":14,"cachedInputPrice":null,"price":"$1.75","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.2-chat","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.2-chat","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":325,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-2-chat","name":"GPT-5.2 Chat","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.2-chat-20251211","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["File","Image","Text","Tools"],"contextWindow":"128000","maxOutputTokens":"32000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":1.75,"outputPrice":14,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-2-pro","slug":"openai-gpt-5-2-pro","canonicalId":"openai-gpt-5-2-pro","name":"GPT-5.2 Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.2-pro-20251211","modalities":["Image","Text","File","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000021,"completion":0.000168},"inputPrice":21,"outputPrice":168,"cachedInputPrice":null,"price":"$21.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.2-pro","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.2-pro","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":326,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-2-pro","name":"GPT-5.2 Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.2-pro-20251211","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Image","Text","File","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":21,"outputPrice":168,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-2-pro-batch","slug":"openai-gpt-5-2-pro-batch","canonicalId":"openai-gpt-5-2-pro-batch","name":"GPT-5.2 Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.2-pro-20251211","modalities":["Image","Text","File","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.0000105,"completion":0.000084},"inputPrice":10.5,"outputPrice":84,"cachedInputPrice":null,"price":"$10.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.2-pro:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.2-pro:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":327,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-2-pro-batch","name":"GPT-5.2 Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.2-pro-20251211","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Image","Text","File","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":10.5,"outputPrice":84,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-devstral-2512","slug":"mistralai-devstral-2512","canonicalId":"mistralai-devstral-2512","name":"Devstral 2 2512","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/devstral-2512","modalities":["Text","File","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"pricing":{"prompt":4e-7,"completion":0.000002},"inputPrice":0.39999999999999997,"outputPrice":2,"cachedInputPrice":null,"price":"$0.40","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":8.6,"coding":31.3,"agents":2.3,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":328,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-devstral-2512","name":"Devstral 2 2512","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/devstral-2512","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","File","Tools"],"contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.39999999999999997,"outputPrice":2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"relace-relace-search","slug":"relace-relace-search","canonicalId":"relace-relace-search","name":"Relace Search","provider":"Relace","family":null,"status":"active","variantType":"base","modelVersion":"relace/relace-search-20251208","modalities":["Text","Tools"],"context_length":"256000","context":"256000","contextWindow":"256000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000003},"inputPrice":1,"outputPrice":3,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":null,"catalogRank":329,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"relace-relace-search","name":"Relace Search","provider":"Relace","family":null,"status":"active","variantType":"base","modelVersion":"relace/relace-search-20251208","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Tools"],"contextWindow":"256000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":1,"outputPrice":3,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-4-6v","slug":"z-ai-glm-4-6v","canonicalId":"z-ai-glm-4-6v","name":"GLM 4.6V","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-4.6-20251208","modalities":["Image","Text","Video","Tools","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":3e-7,"completion":9e-7},"inputPrice":0.3,"outputPrice":0.8999999999999999,"cachedInputPrice":null,"price":"$0.30","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":11.2,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":330,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-4-6v","name":"GLM 4.6V","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-4.6-20251208","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Image","Text","Video","Tools","Reasoning"],"contextWindow":"131072","maxOutputTokens":"32768","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.3,"outputPrice":0.8999999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openrouter-bodybuilder","slug":"openrouter-bodybuilder","canonicalId":"openrouter-bodybuilder","name":"Body Builder (beta)","provider":"OpenRouter","family":null,"status":"active","variantType":"router","modelVersion":"openrouter/bodybuilder","modalities":["Text"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":null,"apiAvailable":true,"pricing":{"prompt":null,"completion":null},"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"price":"N/A","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":null,"catalogRank":331,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openrouter-bodybuilder","name":"Body Builder (beta)","provider":"OpenRouter","family":null,"status":"active","variantType":"router","modelVersion":"openrouter/bodybuilder","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text"],"contextWindow":"128000","maxOutputTokens":null,"apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-1-codex-max","slug":"openai-gpt-5-1-codex-max","canonicalId":"openai-gpt-5-1-codex-max","name":"GPT-5.1-Codex-Max","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.1-codex-max-20251204","modalities":["Text","Image","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00000125,"completion":0.00001},"inputPrice":1.25,"outputPrice":10,"cachedInputPrice":null,"price":"$1.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.1-codex-max","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.1-codex-max","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":332,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-1-codex-max","name":"GPT-5.1-Codex-Max","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.1-codex-max-20251204","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.25,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"amazon-nova-2-lite-v1","slug":"amazon-nova-2-lite-v1","canonicalId":"amazon-nova-2-lite-v1","name":"Nova 2 Lite","provider":"Amazon","family":null,"status":"active","variantType":"fast","modelVersion":"amazon/nova-2-lite-v1","modalities":["Text","Image","Video","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"65535","apiAvailable":true,"pricing":{"prompt":3e-7,"completion":0.0000025},"inputPrice":0.3,"outputPrice":2.5,"cachedInputPrice":null,"price":"$0.30","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":13.4,"coding":23,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aws.amazon.com/"},"pricing":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aws.amazon.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","catalogSourceUrl":"https://aws.amazon.com/","sourceUrl":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=aws.amazon.com&sz=64","catalogRank":333,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"amazon-nova-2-lite-v1","name":"Nova 2 Lite","provider":"Amazon","family":null,"status":"active","variantType":"fast","modelVersion":"amazon/nova-2-lite-v1","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Video","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"65535","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.3,"outputPrice":2.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aws.amazon.com/"},"pricing":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aws.amazon.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-ministral-14b-2512","slug":"mistralai-ministral-14b-2512","canonicalId":"mistralai-ministral-14b-2512","name":"Ministral 3 14B 2512","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/ministral-14b-2512","modalities":["Text","Image","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"pricing":{"prompt":2e-7,"completion":2e-7},"inputPrice":0.19999999999999998,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"price":"$0.20","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":6,"coding":14.4,"agents":1.1,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":334,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-ministral-14b-2512","name":"Ministral 3 14B 2512","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/ministral-14b-2512","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Tools"],"contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.19999999999999998,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-ministral-3b-2512","slug":"mistralai-ministral-3b-2512","canonicalId":"mistralai-ministral-3b-2512","name":"Ministral 3 3B 2512","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/ministral-3b-2512","modalities":["Text","Image","Tools"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"104857","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":1e-7},"inputPrice":0.09999999999999999,"outputPrice":0.09999999999999999,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":4.8,"coding":4.8,"agents":0.8,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":335,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-ministral-3b-2512","name":"Ministral 3 3B 2512","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/ministral-3b-2512","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Tools"],"contextWindow":"131072","maxOutputTokens":"104857","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.09999999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-ministral-8b-2512","slug":"mistralai-ministral-8b-2512","canonicalId":"mistralai-ministral-8b-2512","name":"Ministral 3 8B 2512","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/ministral-8b-2512","modalities":["Text","Image","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"pricing":{"prompt":1.5e-7,"completion":1.5e-7},"inputPrice":0.15,"outputPrice":0.15,"cachedInputPrice":null,"price":"$0.15","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":5.5,"coding":9.7,"agents":0.6,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":336,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-ministral-8b-2512","name":"Ministral 3 8B 2512","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/ministral-8b-2512","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Tools"],"contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.15,"outputPrice":0.15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-ministral-8b-2512-batch","slug":"mistralai-ministral-8b-2512-batch","canonicalId":"mistralai-ministral-8b-2512-batch","name":"Ministral 3 8B 2512 (batch)","provider":"Mistral","family":null,"status":"active","variantType":"batch","modelVersion":"mistralai/ministral-8b-2512","modalities":["Text","Image","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"pricing":{"prompt":7.5e-8,"completion":7.5e-8},"inputPrice":0.075,"outputPrice":0.075,"cachedInputPrice":null,"price":"$0.07","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":5.5,"coding":9.7,"agents":0.6,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":337,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-ministral-8b-2512-batch","name":"Ministral 3 8B 2512 (batch)","provider":"Mistral","family":null,"status":"active","variantType":"batch","modelVersion":"mistralai/ministral-8b-2512","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Image","Tools"],"contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.075,"outputPrice":0.075,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-v3-2","slug":"deepseek-deepseek-v3-2","canonicalId":"deepseek-deepseek-v3-2","name":"DeepSeek V3.2","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"deepseek/deepseek-v3.2-20251201","modalities":["Text","Tools","Reasoning"],"context_length":"163840","context":"163840","contextWindow":"163840","maxOutputTokens":"147456","apiAvailable":true,"pricing":{"prompt":2.59e-7,"completion":8e-7},"inputPrice":0.25899999999999995,"outputPrice":0.7999999999999999,"cachedInputPrice":null,"price":"$0.26","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":21.5,"coding":44.2,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":338,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-v3-2","name":"DeepSeek V3.2","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"deepseek/deepseek-v3.2-20251201","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"163840","maxOutputTokens":"147456","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.25899999999999995,"outputPrice":0.7999999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-mistral-large-2512","slug":"mistralai-mistral-large-2512","canonicalId":"mistralai-mistral-large-2512","name":"Mistral Large 3 2512","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-large-2512","modalities":["Text","Image","File","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"pricing":{"prompt":5e-7,"completion":0.0000015},"inputPrice":0.5,"outputPrice":1.5,"cachedInputPrice":null,"price":"$0.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":9.3,"coding":20.1,"agents":1,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":339,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-mistral-large-2512","name":"Mistral Large 3 2512","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-large-2512","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools"],"contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.5,"outputPrice":1.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-mistral-large-2512-batch","slug":"mistralai-mistral-large-2512-batch","canonicalId":"mistralai-mistral-large-2512-batch","name":"Mistral Large 3 2512 (batch)","provider":"Mistral","family":null,"status":"active","variantType":"batch","modelVersion":"mistralai/mistral-large-2512","modalities":["Text","Image","File","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"pricing":{"prompt":2.5e-7,"completion":7.5e-7},"inputPrice":0.25,"outputPrice":0.75,"cachedInputPrice":null,"price":"$0.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":9.3,"coding":20.1,"agents":1,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":340,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-mistral-large-2512-batch","name":"Mistral Large 3 2512 (batch)","provider":"Mistral","family":null,"status":"active","variantType":"batch","modelVersion":"mistralai/mistral-large-2512","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools"],"contextWindow":"262144","maxOutputTokens":"209715","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.25,"outputPrice":0.75,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-opus-4-5","slug":"anthropic-claude-opus-4-5","canonicalId":"anthropic-claude-opus-4-5","name":"Claude Opus 4.5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4.5-opus-20251124","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"64000","apiAvailable":true,"pricing":{"prompt":0.000005,"completion":0.000025},"inputPrice":5,"outputPrice":25,"cachedInputPrice":null,"price":"$5.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":29.1,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":341,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-opus-4-5","name":"Claude Opus 4.5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4.5-opus-20251124","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"64000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":5,"outputPrice":25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-opus-4-5-batch","slug":"anthropic-claude-opus-4-5-batch","canonicalId":"anthropic-claude-opus-4-5-batch","name":"Claude Opus 4.5 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-4.5-opus-20251124","modalities":["File","Image","Text","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"64000","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.0000125},"inputPrice":2.5,"outputPrice":12.5,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":29.1,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":342,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-opus-4-5-batch","name":"Claude Opus 4.5 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-4.5-opus-20251124","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["File","Image","Text","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"64000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2.5,"outputPrice":12.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"allenai-olmo-3-32b-think","slug":"allenai-olmo-3-32b-think","canonicalId":"allenai-olmo-3-32b-think","name":"Olmo 3 32B Think","provider":"AllenAI","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text","Reasoning"],"context_length":"65536","context":"65536","contextWindow":"65536","maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":1.5e-7,"completion":5e-7},"inputPrice":0.15,"outputPrice":0.5,"cachedInputPrice":null,"price":"$0.15","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://allenai.org/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://allenai.org/"},"pricing":{"name":"Provider source","url":"https://allenai.org/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://allenai.org/"},"metrics":{},"fields":{}},"officialUrl":"https://allenai.org/","catalogSourceUrl":"https://allenai.org/","sourceUrl":"https://allenai.org/","sourceUpdatedAt":{},"updated":"2026-08-28","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=allenai.org&sz=64","catalogRank":343,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"allenai-olmo-3-32b-think","name":"Olmo 3 32B Think","provider":"AllenAI","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Reasoning"],"contextWindow":"65536","maxOutputTokens":null,"apiAvailable":null,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"inputPrice":0.15,"outputPrice":0.5,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Provider source","url":"https://allenai.org/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://allenai.org/"},"pricing":{"name":"Provider source","url":"https://allenai.org/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://allenai.org/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-3-pro-image-preview","slug":"google-gemini-3-pro-image-preview","canonicalId":"google-gemini-3-pro-image-preview","name":"Nano Banana Pro (Gemini 3 Pro Image Preview)","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/gemini-3-pro-image-preview-20251120","modalities":["Image","Text","Reasoning"],"context_length":"65536","context":"65536","contextWindow":"65536","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000012},"inputPrice":2,"outputPrice":12,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":344,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-3-pro-image-preview","name":"Nano Banana Pro (Gemini 3 Pro Image Preview)","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/gemini-3-pro-image-preview-20251120","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Image","Text","Reasoning"],"contextWindow":"65536","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":12,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-1","slug":"openai-gpt-5-1","canonicalId":"openai-gpt-5-1","name":"GPT-5.1","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.1-20251113","modalities":["Image","Text","File","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00000125,"completion":0.00001},"inputPrice":1.25,"outputPrice":10,"cachedInputPrice":null,"price":"$1.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":24.7,"coding":49.4,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.1","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.1","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":345,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-1","name":"GPT-5.1","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.1-20251113","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Image","Text","File","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.25,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-1-batch","slug":"openai-gpt-5-1-batch","canonicalId":"openai-gpt-5-1-batch","name":"GPT-5.1 (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.1-20251113","modalities":["Image","Text","File","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":6.25e-7,"completion":0.000005},"inputPrice":0.625,"outputPrice":5,"cachedInputPrice":null,"price":"$0.63","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":24.7,"coding":49.4,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.1:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.1:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":346,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-1-batch","name":"GPT-5.1 (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5.1-20251113","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Image","Text","File","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.625,"outputPrice":5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-1-codex","slug":"openai-gpt-5-1-codex","canonicalId":"openai-gpt-5-1-codex","name":"GPT-5.1-Codex","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.1-codex-20251113","modalities":["Text","Image","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00000125,"completion":0.00001},"inputPrice":1.25,"outputPrice":10,"cachedInputPrice":null,"price":"$1.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":23.7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.1-codex","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.1-codex","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":347,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-1-codex","name":"GPT-5.1-Codex","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5.1-codex-20251113","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.25,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-1-codex-mini","slug":"openai-gpt-5-1-codex-mini","canonicalId":"openai-gpt-5-1-codex-mini","name":"GPT-5.1-Codex-Mini","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/gpt-5.1-codex-mini-20251113","modalities":["Image","Text","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":2.5e-7,"completion":0.000002},"inputPrice":0.25,"outputPrice":2,"cachedInputPrice":null,"price":"$0.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":20.4,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5.1-codex-mini","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5.1-codex-mini","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":348,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-1-codex-mini","name":"GPT-5.1-Codex-Mini","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/gpt-5.1-codex-mini-20251113","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Image","Text","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.25,"outputPrice":2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"amazon-nova-premier-v1","slug":"amazon-nova-premier-v1","canonicalId":"amazon-nova-premier-v1","name":"Nova Premier 1.0","provider":"Amazon","family":null,"status":"active","variantType":"base","modelVersion":"amazon/nova-premier-v1","modalities":["Text","Image","Tools"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"32000","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.0000125},"inputPrice":2.5,"outputPrice":12.5,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":9.2,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aws.amazon.com/"},"pricing":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aws.amazon.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","catalogSourceUrl":"https://aws.amazon.com/","sourceUrl":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=aws.amazon.com&sz=64","catalogRank":349,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"amazon-nova-premier-v1","name":"Nova Premier 1.0","provider":"Amazon","family":null,"status":"active","variantType":"base","modelVersion":"amazon/nova-premier-v1","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Tools"],"contextWindow":"1000000","maxOutputTokens":"32000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":2.5,"outputPrice":12.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aws.amazon.com/"},"pricing":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aws.amazon.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-voxtral-small-24b-2507","slug":"mistralai-voxtral-small-24b-2507","canonicalId":"mistralai-voxtral-small-24b-2507","name":"Voxtral Small 24B 2507","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/voxtral-small-24b-2507","modalities":["Text","Audio","File","Tools"],"context_length":"32768","context":"32768","contextWindow":"32768","maxOutputTokens":"26214","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":3e-7},"inputPrice":0.09999999999999999,"outputPrice":0.3,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":350,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-voxtral-small-24b-2507","name":"Voxtral Small 24B 2507","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/voxtral-small-24b-2507","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Audio","File","Tools"],"contextWindow":"32768","maxOutputTokens":"26214","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.3,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"perplexity-sonar-pro-search","slug":"perplexity-sonar-pro-search","canonicalId":"perplexity-sonar-pro-search","name":"Sonar Pro Search","provider":"Perplexity","family":null,"status":"active","variantType":"base","modelVersion":"perplexity/sonar-pro-search","modalities":["Text","Image","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"8000","apiAvailable":true,"pricing":{"prompt":0.000003,"completion":0.000015},"inputPrice":3,"outputPrice":15,"cachedInputPrice":null,"price":"$3.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://perplexity.ai/"},"pricing":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://perplexity.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.perplexity.ai/getting-started/models","catalogSourceUrl":"https://perplexity.ai/","sourceUrl":"https://docs.perplexity.ai/getting-started/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":true,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=perplexity.ai&sz=64","catalogRank":351,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"perplexity-sonar-pro-search","name":"Sonar Pro Search","provider":"Perplexity","family":null,"status":"active","variantType":"base","modelVersion":"perplexity/sonar-pro-search","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Reasoning"],"contextWindow":"200000","maxOutputTokens":"8000","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":true,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":3,"outputPrice":15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://perplexity.ai/"},"pricing":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://perplexity.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-oss-safeguard-20b","slug":"openai-gpt-oss-safeguard-20b","canonicalId":"openai-gpt-oss-safeguard-20b","name":"gpt-oss-safeguard-20b","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-oss-safeguard-20b","modalities":["Text","Tools","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":7.5e-8,"completion":3e-7},"inputPrice":0.075,"outputPrice":0.3,"cachedInputPrice":null,"price":"$0.07","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-oss-safeguard-20b","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-oss-safeguard-20b","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":352,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-oss-safeguard-20b","name":"gpt-oss-safeguard-20b","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-oss-safeguard-20b","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"131072","maxOutputTokens":"65536","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.075,"outputPrice":0.3,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"minimax-minimax-m2","slug":"minimax-minimax-m2","canonicalId":"minimax-minimax-m2","name":"MiniMax M2","provider":"MiniMax","family":null,"status":"active","variantType":"base","modelVersion":"minimax/minimax-m2","modalities":["Text","Tools","Reasoning"],"context_length":"204800","context":"204800","contextWindow":"204800","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":2.55e-7,"completion":0.00000102},"inputPrice":0.255,"outputPrice":1.02,"cachedInputPrice":null,"price":"$0.26","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":18.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}},"officialUrl":"https://platform.minimax.io/docs/guides/models","catalogSourceUrl":"https://minimax.io/","sourceUrl":"https://platform.minimax.io/docs/guides/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=minimax.io&sz=64","catalogRank":353,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"minimax-minimax-m2","name":"MiniMax M2","provider":"MiniMax","family":null,"status":"active","variantType":"base","modelVersion":"minimax/minimax-m2","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"204800","maxOutputTokens":"131072","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.255,"outputPrice":1.02,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"ibm-granite-granite-4-0-h-micro","slug":"ibm-granite-granite-4-0-h-micro","canonicalId":"ibm-granite-granite-4-0-h-micro","name":"Granite 4.0 Micro","provider":"IBM","family":null,"status":"active","variantType":"base","modelVersion":"ibm-granite/granite-4.0-h-micro","modalities":["Text"],"context_length":"131000","context":"131000","contextWindow":"131000","maxOutputTokens":"117900","apiAvailable":true,"pricing":{"prompt":1.7e-8,"completion":1.12e-7},"inputPrice":0.017,"outputPrice":0.112,"cachedInputPrice":null,"price":"$0.02","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":5.1,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ibm.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ibm.com/"},"pricing":{"name":"Provider source","url":"https://ibm.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ibm.com/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://ibm.com/","sourceUrl":"https://ibm.com/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=ibm.com&sz=64","catalogRank":354,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"ibm-granite-granite-4-0-h-micro","name":"Granite 4.0 Micro","provider":"IBM","family":null,"status":"active","variantType":"base","modelVersion":"ibm-granite/granite-4.0-h-micro","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text"],"contextWindow":"131000","maxOutputTokens":"117900","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.017,"outputPrice":0.112,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ibm.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ibm.com/"},"pricing":{"name":"Provider source","url":"https://ibm.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ibm.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-image-mini","slug":"openai-gpt-5-image-mini","canonicalId":"openai-gpt-5-image-mini","name":"GPT-5 Image Mini","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/gpt-5-image-mini","modalities":["File","Image","Text","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.000002},"inputPrice":2.5,"outputPrice":2,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5-image-mini","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5-image-mini","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":355,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-image-mini","name":"GPT-5 Image Mini","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/gpt-5-image-mini","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["File","Image","Text","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2.5,"outputPrice":2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-haiku-4-5","slug":"anthropic-claude-haiku-4-5","canonicalId":"anthropic-claude-haiku-4-5","name":"Claude Haiku 4.5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4.5-haiku-20251001","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"64000","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000005},"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":16.9,"coding":43.9,"agents":8,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":356,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-haiku-4-5","name":"Claude Haiku 4.5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4.5-haiku-20251001","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"64000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-haiku-4-5-batch","slug":"anthropic-claude-haiku-4-5-batch","canonicalId":"anthropic-claude-haiku-4-5-batch","name":"Claude Haiku 4.5 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-4.5-haiku-20251001","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"64000","apiAvailable":true,"pricing":{"prompt":5e-7,"completion":0.0000025},"inputPrice":0.5,"outputPrice":2.5,"cachedInputPrice":null,"price":"$0.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":16.9,"coding":43.9,"agents":8,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":357,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-haiku-4-5-batch","name":"Claude Haiku 4.5 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-4.5-haiku-20251001","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"64000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.5,"outputPrice":2.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-image","slug":"openai-gpt-5-image","canonicalId":"openai-gpt-5-image","name":"GPT-5 Image","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5-image","modalities":["Image","Text","File","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.00001,"completion":0.00001},"inputPrice":10,"outputPrice":10,"cachedInputPrice":null,"price":"$10.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5-image","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5-image","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":358,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-image","name":"GPT-5 Image","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5-image","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Image","Text","File","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":10,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-vl-8b-instruct","slug":"qwen-qwen3-vl-8b-instruct","canonicalId":"qwen-qwen3-vl-8b-instruct","name":"Qwen3 VL 8B Instruct","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-vl-8b-instruct","modalities":["Image","Text","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":2.5e-7,"completion":7.5e-7},"inputPrice":0.25,"outputPrice":0.75,"cachedInputPrice":null,"price":"$0.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7.3,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":359,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-vl-8b-instruct","name":"Qwen3 VL 8B Instruct","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-vl-8b-instruct","releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Image","Text","Tools"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.25,"outputPrice":0.75,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-2-5-flash-image","slug":"google-gemini-2-5-flash-image","canonicalId":"google-gemini-2-5-flash-image","name":"Nano Banana (Gemini 2.5 Flash Image)","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-2.5-flash-image","modalities":["Image","Text"],"context_length":"32768","context":"32768","contextWindow":"32768","maxOutputTokens":"8192","apiAvailable":true,"pricing":{"prompt":3e-7,"completion":0.0000025},"inputPrice":0.3,"outputPrice":2.5,"cachedInputPrice":null,"price":"$0.30","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":360,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-2-5-flash-image","name":"Nano Banana (Gemini 2.5 Flash Image)","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-2.5-flash-image","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text"],"contextWindow":"32768","maxOutputTokens":"8192","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.3,"outputPrice":2.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-pro","slug":"openai-gpt-5-pro","canonicalId":"openai-gpt-5-pro","name":"GPT-5 Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5-pro-2025-10-06","modalities":["Image","Text","File","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.000015,"completion":0.00012},"inputPrice":15,"outputPrice":120,"cachedInputPrice":null,"price":"$15.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5-pro","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5-pro","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":361,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-pro","name":"GPT-5 Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5-pro-2025-10-06","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text","File","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":15,"outputPrice":120,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-pro-batch","slug":"openai-gpt-5-pro-batch","canonicalId":"openai-gpt-5-pro-batch","name":"GPT-5 Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5-pro-2025-10-06","modalities":["Image","Text","File","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":0.0000075,"completion":0.00006},"inputPrice":7.5,"outputPrice":60,"cachedInputPrice":null,"price":"$7.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5-pro:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5-pro:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":362,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-pro-batch","name":"GPT-5 Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5-pro-2025-10-06","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text","File","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":7.5,"outputPrice":60,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-vl-30b-a3b-instruct","slug":"qwen-qwen3-vl-30b-a3b-instruct","canonicalId":"qwen-qwen3-vl-30b-a3b-instruct","name":"Qwen3 VL 30B A3B Instruct","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-vl-30b-a3b-instruct","modalities":["Text","Image","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":1.5e-7,"completion":6e-7},"inputPrice":0.15,"outputPrice":0.6,"cachedInputPrice":null,"price":"$0.15","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7.9,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":363,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-vl-30b-a3b-instruct","name":"Qwen3 VL 30B A3B Instruct","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-vl-30b-a3b-instruct","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Image","Tools"],"contextWindow":"262144","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.15,"outputPrice":0.6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-vl-30b-a3b-thinking","slug":"qwen-qwen3-vl-30b-a3b-thinking","canonicalId":"qwen-qwen3-vl-30b-a3b-thinking","name":"Qwen3 VL 30B A3B Thinking","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-vl-30b-a3b-thinking","modalities":["Text","Image","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":2.9e-7,"completion":0.000001},"inputPrice":0.29,"outputPrice":1,"cachedInputPrice":null,"price":"$0.29","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":9.5,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":364,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-vl-30b-a3b-thinking","name":"Qwen3 VL 30B A3B Thinking","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-vl-30b-a3b-thinking","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.29,"outputPrice":1,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-4-6","slug":"z-ai-glm-4-6","canonicalId":"z-ai-glm-4-6","name":"GLM 4.6","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-4.6","modalities":["Text","Tools","Reasoning"],"context_length":"204800","context":"204800","contextWindow":"204800","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":5e-7,"completion":0.000002},"inputPrice":0.5,"outputPrice":2,"cachedInputPrice":null,"price":"$0.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":18.5,"coding":45.8,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":365,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-4-6","name":"GLM 4.6","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-4.6","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"204800","maxOutputTokens":"131072","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.5,"outputPrice":2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-sonnet-4-5","slug":"anthropic-claude-sonnet-4-5","canonicalId":"anthropic-claude-sonnet-4-5","name":"Claude Sonnet 4.5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4.5-sonnet-20250929","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"64000","apiAvailable":true,"pricing":{"prompt":0.000003,"completion":0.000015},"inputPrice":3,"outputPrice":15,"cachedInputPrice":null,"price":"$3.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":20.7,"coding":52.1,"agents":15.8,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":366,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-sonnet-4-5","name":"Claude Sonnet 4.5","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4.5-sonnet-20250929","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"64000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":3,"outputPrice":15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-sonnet-4-5-batch","slug":"anthropic-claude-sonnet-4-5-batch","canonicalId":"anthropic-claude-sonnet-4-5-batch","name":"Claude Sonnet 4.5 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-4.5-sonnet-20250929","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"64000","apiAvailable":true,"pricing":{"prompt":0.0000015,"completion":0.0000075},"inputPrice":1.5,"outputPrice":7.5,"cachedInputPrice":null,"price":"$1.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":20.7,"coding":52.1,"agents":15.8,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":367,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-sonnet-4-5-batch","name":"Claude Sonnet 4.5 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-4.5-sonnet-20250929","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"64000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.5,"outputPrice":7.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-v3-2-exp","slug":"deepseek-deepseek-v3-2-exp","canonicalId":"deepseek-deepseek-v3-2-exp","name":"DeepSeek V3.2 Exp","provider":"DeepSeek","family":null,"status":"active","variantType":"preview","modelVersion":"deepseek/deepseek-v3.2-exp","modalities":["Text","Tools","Reasoning"],"context_length":"163840","context":"163840","contextWindow":"163840","maxOutputTokens":"147456","apiAvailable":true,"pricing":{"prompt":2.7e-7,"completion":4.1e-7},"inputPrice":0.27,"outputPrice":0.41,"cachedInputPrice":null,"price":"$0.27","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":16.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":368,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-v3-2-exp","name":"DeepSeek V3.2 Exp","provider":"DeepSeek","family":null,"status":"active","variantType":"preview","modelVersion":"deepseek/deepseek-v3.2-exp","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"163840","maxOutputTokens":"147456","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.27,"outputPrice":0.41,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"thedrummer-cydonia-24b-v4-1","slug":"thedrummer-cydonia-24b-v4-1","canonicalId":"thedrummer-cydonia-24b-v4-1","name":"Cydonia 24B V4.1","provider":"TheDrummer","family":null,"status":"active","variantType":"base","modelVersion":"thedrummer/cydonia-24b-v4.1","modalities":["Text"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"pricing":{"prompt":3e-7,"completion":5e-7},"inputPrice":0.3,"outputPrice":0.5,"cachedInputPrice":null,"price":"$0.30","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":369,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"thedrummer-cydonia-24b-v4-1","name":"Cydonia 24B V4.1","provider":"TheDrummer","family":null,"status":"active","variantType":"base","modelVersion":"thedrummer/cydonia-24b-v4.1","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.3,"outputPrice":0.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"relace-relace-apply-3","slug":"relace-relace-apply-3","canonicalId":"relace-relace-apply-3","name":"Relace Apply 3","provider":"Relace","family":null,"status":"active","variantType":"base","modelVersion":"relace/relace-apply-3","modalities":["Text"],"context_length":"256000","context":"256000","contextWindow":"256000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":8.5e-7,"completion":0.00000125},"inputPrice":0.85,"outputPrice":1.25,"cachedInputPrice":null,"price":"$0.85","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":null,"catalogRank":370,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"relace-relace-apply-3","name":"Relace Apply 3","provider":"Relace","family":null,"status":"active","variantType":"base","modelVersion":"relace/relace-apply-3","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text"],"contextWindow":"256000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.85,"outputPrice":1.25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-codex-batch","slug":"openai-gpt-5-codex-batch","canonicalId":"openai-gpt-5-codex-batch","name":"GPT-5 Codex (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text","Image","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":6.25e-7,"completion":0.000005},"inputPrice":0.625,"outputPrice":5,"cachedInputPrice":null,"price":"$0.63","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://openai.com/","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://openai.com/","sourceUpdatedAt":{},"updated":"2026-08-27","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":371,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-codex-batch","name":"GPT-5 Codex (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":null,"apiAvailable":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"inputPrice":0.625,"outputPrice":5,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-vl-235b-a22b-instruct","slug":"qwen-qwen3-vl-235b-a22b-instruct","canonicalId":"qwen-qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-vl-235b-a22b-instruct","modalities":["Text","Image","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":2.1e-7,"completion":0.0000018999999999999998},"inputPrice":0.21,"outputPrice":1.9,"cachedInputPrice":null,"price":"$0.21","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":9.9,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":372,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-vl-235b-a22b-instruct","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Image","Tools"],"contextWindow":"262144","maxOutputTokens":"32768","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.21,"outputPrice":1.9,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-v3-1-terminus","slug":"deepseek-deepseek-v3-1-terminus","canonicalId":"deepseek-deepseek-v3-1-terminus","name":"DeepSeek V3.1 Terminus","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"deepseek/deepseek-v3.1-terminus","modalities":["Text","Tools","Reasoning"],"context_length":"163840","context":"163840","contextWindow":"163840","maxOutputTokens":"147456","apiAvailable":true,"pricing":{"prompt":2.7e-7,"completion":0.000001},"inputPrice":0.27,"outputPrice":1,"cachedInputPrice":null,"price":"$0.27","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":14.8,"coding":43.5,"agents":6.8,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":373,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-v3-1-terminus","name":"DeepSeek V3.1 Terminus","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"deepseek/deepseek-v3.1-terminus","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"163840","maxOutputTokens":"147456","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.27,"outputPrice":1,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-coder-flash","slug":"qwen-qwen3-coder-flash","canonicalId":"qwen-qwen3-coder-flash","name":"Qwen3 Coder Flash","provider":"Qwen","family":null,"status":"active","variantType":"fast","modelVersion":"qwen/qwen3-coder-flash","modalities":["Text","Tools"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":1.95e-7,"completion":9.75e-7},"inputPrice":0.195,"outputPrice":0.975,"cachedInputPrice":null,"price":"$0.20","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":374,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-coder-flash","name":"Qwen3 Coder Flash","provider":"Qwen","family":null,"status":"active","variantType":"fast","modelVersion":"qwen/qwen3-coder-flash","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Tools"],"contextWindow":"1000000","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.195,"outputPrice":0.975,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-next-80b-a3b-instruct","slug":"qwen-qwen3-next-80b-a3b-instruct","canonicalId":"qwen-qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-next-80b-a3b-instruct-2509","modalities":["Text","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":0.0000011},"inputPrice":0.09999999999999999,"outputPrice":1.1,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":9.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":375,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-next-80b-a3b-instruct-2509","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":1.1,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-next-80b-a3b-thinking","slug":"qwen-qwen3-next-80b-a3b-thinking","canonicalId":"qwen-qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-next-80b-a3b-thinking-2509","modalities":["Text","Tools","Reasoning"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":1.5e-7,"completion":0.0000012},"inputPrice":0.15,"outputPrice":1.2,"cachedInputPrice":null,"price":"$0.15","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":11.2,"coding":17.4,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":376,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-next-80b-a3b-thinking-2509","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.15,"outputPrice":1.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen-plus-2025-07-28-thinking","slug":"qwen-qwen-plus-2025-07-28-thinking","canonicalId":"qwen-qwen-plus-2025-07-28-thinking","name":"Qwen Plus 0728 (thinking)","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":2.6e-7,"completion":7.8e-7},"inputPrice":0.26,"outputPrice":0.78,"cachedInputPrice":null,"price":"$0.26","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwen.ai/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwen.ai/","sourceUpdatedAt":{},"updated":"2026-08-25","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":377,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen-plus-2025-07-28-thinking","name":"Qwen Plus 0728 (thinking)","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":null,"apiAvailable":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"inputPrice":0.26,"outputPrice":0.78,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"moonshotai-kimi-k2-0905","slug":"moonshotai-kimi-k2-0905","canonicalId":"moonshotai-kimi-k2-0905","name":"Kimi K2 0905","provider":"Moonshot AI","family":null,"status":"active","variantType":"base","modelVersion":"moonshotai/kimi-k2-0905","modalities":["Text","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"98304","apiAvailable":true,"pricing":{"prompt":6e-7,"completion":0.0000025},"inputPrice":0.6,"outputPrice":2.5,"cachedInputPrice":null,"price":"$0.60","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":15.3,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://platform.moonshot.ai/docs/guide/models","catalogSourceUrl":"https://moonshot.ai/","sourceUrl":"https://platform.moonshot.ai/docs/guide/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=moonshot.ai&sz=64","catalogRank":378,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"moonshotai-kimi-k2-0905","name":"Kimi K2 0905","provider":"Moonshot AI","family":null,"status":"active","variantType":"base","modelVersion":"moonshotai/kimi-k2-0905","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools"],"contextWindow":"262144","maxOutputTokens":"98304","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.6,"outputPrice":2.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"nousresearch-hermes-4-405b","slug":"nousresearch-hermes-4-405b","canonicalId":"nousresearch-hermes-4-405b","name":"Hermes 4 405B","provider":"Nous","family":null,"status":"active","variantType":"base","modelVersion":"nousresearch/hermes-4-405b","modalities":["Text","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000003},"inputPrice":1,"outputPrice":3,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7.5,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":379,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"nousresearch-hermes-4-405b","name":"Hermes 4 405B","provider":"Nous","family":null,"status":"active","variantType":"base","modelVersion":"nousresearch/hermes-4-405b","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Reasoning"],"contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":1,"outputPrice":3,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"nousresearch-hermes-4-70b","slug":"nousresearch-hermes-4-70b","canonicalId":"nousresearch-hermes-4-70b","name":"Hermes 4 70B","provider":"Nous","family":null,"status":"active","variantType":"base","modelVersion":"nousresearch/hermes-4-70b","modalities":["Text","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"pricing":{"prompt":1.3e-7,"completion":4e-7},"inputPrice":0.13,"outputPrice":0.39999999999999997,"cachedInputPrice":null,"price":"$0.13","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-09-09","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":380,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"nousresearch-hermes-4-70b","name":"Hermes 4 70B","provider":"Nous","family":null,"status":"active","variantType":"base","modelVersion":"nousresearch/hermes-4-70b","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Reasoning"],"contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.13,"outputPrice":0.39999999999999997,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-chat-v3-1","slug":"deepseek-deepseek-chat-v3-1","canonicalId":"deepseek-deepseek-chat-v3-1","name":"DeepSeek V3.1","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"deepseek/deepseek-chat-v3.1","modalities":["Text","Tools","Reasoning"],"context_length":"163840","context":"163840","contextWindow":"163840","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":2.5e-7,"completion":9.499999999999999e-7},"inputPrice":0.25,"outputPrice":0.95,"cachedInputPrice":null,"price":"$0.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":13.7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":381,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-chat-v3-1","name":"DeepSeek V3.1","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"deepseek/deepseek-chat-v3.1","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"163840","maxOutputTokens":"32768","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.25,"outputPrice":0.95,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-mistral-medium-3-1","slug":"mistralai-mistral-medium-3-1","canonicalId":"mistralai-mistral-medium-3-1","name":"Mistral Medium 3.1","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-medium-3.1","modalities":["Text","Image","File","Tools"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"104857","apiAvailable":true,"pricing":{"prompt":4e-7,"completion":0.000002},"inputPrice":0.39999999999999997,"outputPrice":2,"cachedInputPrice":null,"price":"$0.40","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":9.2,"coding":20.5,"agents":1.9,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":382,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-mistral-medium-3-1","name":"Mistral Medium 3.1","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-medium-3.1","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools"],"contextWindow":"131072","maxOutputTokens":"104857","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.39999999999999997,"outputPrice":2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-mistral-medium-3-1-batch","slug":"mistralai-mistral-medium-3-1-batch","canonicalId":"mistralai-mistral-medium-3-1-batch","name":"Mistral Medium 3.1 (batch)","provider":"Mistral","family":null,"status":"active","variantType":"batch","modelVersion":"mistralai/mistral-medium-3.1","modalities":["Text","Image","File","Tools"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"104857","apiAvailable":true,"pricing":{"prompt":2e-7,"completion":0.000001},"inputPrice":0.19999999999999998,"outputPrice":1,"cachedInputPrice":null,"price":"$0.20","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":9.2,"coding":20.5,"agents":1.9,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":383,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-mistral-medium-3-1-batch","name":"Mistral Medium 3.1 (batch)","provider":"Mistral","family":null,"status":"active","variantType":"batch","modelVersion":"mistralai/mistral-medium-3.1","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools"],"contextWindow":"131072","maxOutputTokens":"104857","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.19999999999999998,"outputPrice":1,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-4-5v","slug":"z-ai-glm-4-5v","canonicalId":"z-ai-glm-4-5v","name":"GLM 4.5V","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-4.5v","modalities":["Text","Image","Tools","Reasoning"],"context_length":"65536","context":"65536","contextWindow":"65536","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":6e-7,"completion":0.0000018},"inputPrice":0.6,"outputPrice":1.7999999999999998,"cachedInputPrice":null,"price":"$0.60","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":384,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-4-5v","name":"GLM 4.5V","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-4.5v","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Image","Tools","Reasoning"],"contextWindow":"65536","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.6,"outputPrice":1.7999999999999998,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-batch","slug":"openai-gpt-5-batch","canonicalId":"openai-gpt-5-batch","name":"GPT-5 (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5-2025-08-07","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":6.25e-7,"completion":0.000005},"inputPrice":0.625,"outputPrice":5,"cachedInputPrice":null,"price":"$0.63","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":23,"coding":37.8,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":385,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-batch","name":"GPT-5 (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5-2025-08-07","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.625,"outputPrice":5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-mini","slug":"openai-gpt-5-mini","canonicalId":"openai-gpt-5-mini","name":"GPT-5 Mini","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/gpt-5-mini-2025-08-07","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":2.5e-7,"completion":0.000002},"inputPrice":0.25,"outputPrice":2,"cachedInputPrice":null,"price":"$0.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":20.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5-mini","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5-mini","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":386,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-mini","name":"GPT-5 Mini","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/gpt-5-mini-2025-08-07","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.25,"outputPrice":2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-mini-batch","slug":"openai-gpt-5-mini-batch","canonicalId":"openai-gpt-5-mini-batch","name":"GPT-5 Mini (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5-mini-2025-08-07","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":1.25e-7,"completion":0.000001},"inputPrice":0.125,"outputPrice":1,"cachedInputPrice":null,"price":"$0.13","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":20.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5-mini:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5-mini:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":387,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-mini-batch","name":"GPT-5 Mini (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5-mini-2025-08-07","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.125,"outputPrice":1,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-nano","slug":"openai-gpt-5-nano","canonicalId":"openai-gpt-5-nano","name":"GPT-5 Nano","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5-nano-2025-08-07","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":5e-8,"completion":4e-7},"inputPrice":0.049999999999999996,"outputPrice":0.39999999999999997,"cachedInputPrice":null,"price":"$0.05","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":13,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5-nano","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5-nano","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":388,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-nano","name":"GPT-5 Nano","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-5-nano-2025-08-07","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.049999999999999996,"outputPrice":0.39999999999999997,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-5-nano-batch","slug":"openai-gpt-5-nano-batch","canonicalId":"openai-gpt-5-nano-batch","name":"GPT-5 Nano (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5-nano-2025-08-07","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"400000","context":"400000","contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"pricing":{"prompt":2.5e-8,"completion":2e-7},"inputPrice":0.024999999999999998,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"price":"$0.02","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":13,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-5-nano:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-5-nano:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":389,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-5-nano-batch","name":"GPT-5 Nano (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-5-nano-2025-08-07","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"400000","maxOutputTokens":"128000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.024999999999999998,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-opus-4-1","slug":"anthropic-claude-opus-4-1","canonicalId":"anthropic-claude-opus-4-1","name":"Claude Opus 4.1","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4.1-opus-20250805","modalities":["Image","Text","File","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"32000","apiAvailable":true,"pricing":{"prompt":0.000015,"completion":0.000075},"inputPrice":15,"outputPrice":75,"cachedInputPrice":null,"price":"$15.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":22.8,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":390,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-opus-4-1","name":"Claude Opus 4.1","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4.1-opus-20250805","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text","File","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"32000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":15,"outputPrice":75,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-opus-4-1-batch","slug":"anthropic-claude-opus-4-1-batch","canonicalId":"anthropic-claude-opus-4-1-batch","name":"Claude Opus 4.1 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-4.1-opus-20250805","modalities":["Image","Text","File","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"32000","apiAvailable":true,"pricing":{"prompt":0.0000075,"completion":0.0000375},"inputPrice":7.5,"outputPrice":37.5,"cachedInputPrice":null,"price":"$7.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":22.8,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":391,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-opus-4-1-batch","name":"Claude Opus 4.1 (batch)","provider":"Anthropic","family":null,"status":"active","variantType":"batch","modelVersion":"anthropic/claude-4.1-opus-20250805","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text","File","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"32000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":7.5,"outputPrice":37.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-oss-120b-batch","slug":"openai-gpt-oss-120b-batch","canonicalId":"openai-gpt-oss-120b-batch","name":"gpt-oss-120b (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-oss-120b","modalities":["Text","Tools","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"pricing":{"prompt":2.96e-8,"completion":1.36e-7},"inputPrice":0.0296,"outputPrice":0.136,"cachedInputPrice":null,"price":"$0.03","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":11.6,"coding":30.4,"agents":3.7,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-oss-120b:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-oss-120b:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":392,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-oss-120b-batch","name":"gpt-oss-120b (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-oss-120b","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.0296,"outputPrice":0.136,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-oss-20b-batch","slug":"openai-gpt-oss-20b-batch","canonicalId":"openai-gpt-oss-20b-batch","name":"gpt-oss-20b (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-oss-20b","modalities":["Text","Tools","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"pricing":{"prompt":2.4e-8,"completion":1.12e-7},"inputPrice":0.024,"outputPrice":0.112,"cachedInputPrice":null,"price":"$0.02","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":10,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-oss-20b:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-oss-20b:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":393,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-oss-20b-batch","name":"gpt-oss-20b (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-oss-20b","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.024,"outputPrice":0.112,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-codestral-2508","slug":"mistralai-codestral-2508","canonicalId":"mistralai-codestral-2508","name":"Codestral 2508","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/codestral-2508","modalities":["Text","File","Tools"],"context_length":"256000","context":"256000","contextWindow":"256000","maxOutputTokens":"204800","apiAvailable":true,"pricing":{"prompt":3e-7,"completion":9e-7},"inputPrice":0.3,"outputPrice":0.8999999999999999,"cachedInputPrice":null,"price":"$0.30","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":394,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-codestral-2508","name":"Codestral 2508","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/codestral-2508","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","File","Tools"],"contextWindow":"256000","maxOutputTokens":"204800","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.3,"outputPrice":0.8999999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-codestral-2508-batch","slug":"mistralai-codestral-2508-batch","canonicalId":"mistralai-codestral-2508-batch","name":"Codestral 2508 (batch)","provider":"Mistral","family":null,"status":"active","variantType":"batch","modelVersion":"mistralai/codestral-2508","modalities":["Text","File","Tools"],"context_length":"256000","context":"256000","contextWindow":"256000","maxOutputTokens":"204800","apiAvailable":true,"pricing":{"prompt":1.5e-7,"completion":4.5e-7},"inputPrice":0.15,"outputPrice":0.44999999999999996,"cachedInputPrice":null,"price":"$0.15","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":395,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-codestral-2508-batch","name":"Codestral 2508 (batch)","provider":"Mistral","family":null,"status":"active","variantType":"batch","modelVersion":"mistralai/codestral-2508","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","File","Tools"],"contextWindow":"256000","maxOutputTokens":"204800","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.15,"outputPrice":0.44999999999999996,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-coder-30b-a3b-instruct","slug":"qwen-qwen3-coder-30b-a3b-instruct","canonicalId":"qwen-qwen3-coder-30b-a3b-instruct","name":"Qwen3 Coder 30B A3B Instruct","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-coder-30b-a3b-instruct","modalities":["Text","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":7e-8,"completion":2.8e-7},"inputPrice":0.07,"outputPrice":0.28,"cachedInputPrice":null,"price":"$0.07","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":9.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":396,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-coder-30b-a3b-instruct","name":"Qwen3 Coder 30B A3B Instruct","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-coder-30b-a3b-instruct","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.07,"outputPrice":0.28,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-30b-a3b-instruct-2507","slug":"qwen-qwen3-30b-a3b-instruct-2507","canonicalId":"qwen-qwen3-30b-a3b-instruct-2507","name":"Qwen3 30B A3B Instruct 2507","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-30b-a3b-instruct-2507","modalities":["Text","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":3e-7},"inputPrice":0.09999999999999999,"outputPrice":0.3,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7.5,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":397,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-30b-a3b-instruct-2507","name":"Qwen3 30B A3B Instruct 2507","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-30b-a3b-instruct-2507","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools"],"contextWindow":"262144","maxOutputTokens":"235929","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.3,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-235b-a22b-thinking-2507","slug":"qwen-qwen3-235b-a22b-thinking-2507","canonicalId":"qwen-qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22B Thinking 2507","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-235b-a22b-thinking-2507","modalities":["Text","Tools","Reasoning"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":4.5e-7,"completion":0.0000035},"inputPrice":0.44999999999999996,"outputPrice":3.5,"cachedInputPrice":null,"price":"$0.45","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":12.7,"coding":22.1,"agents":1.3,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":398,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22B Thinking 2507","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-235b-a22b-thinking-2507","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.44999999999999996,"outputPrice":3.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-4-5","slug":"z-ai-glm-4-5","canonicalId":"z-ai-glm-4-5","name":"GLM 4.5","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-4.5","modalities":["Text","Tools","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"98304","apiAvailable":true,"pricing":{"prompt":6e-7,"completion":0.0000022},"inputPrice":0.6,"outputPrice":2.2,"cachedInputPrice":null,"price":"$0.60","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":12.8,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":399,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-4-5","name":"GLM 4.5","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-4.5","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"131072","maxOutputTokens":"98304","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.6,"outputPrice":2.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"z-ai-glm-4-5-air","slug":"z-ai-glm-4-5-air","canonicalId":"z-ai-glm-4-5-air","name":"GLM 4.5 Air","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-4.5-air","modalities":["Text","Tools","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"98304","apiAvailable":true,"pricing":{"prompt":1.3e-7,"completion":8.5e-7},"inputPrice":0.13,"outputPrice":0.85,"cachedInputPrice":null,"price":"$0.13","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":11.1,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.z.ai/guides/overview/models","catalogSourceUrl":"https://z.ai/","sourceUrl":"https://docs.z.ai/guides/overview/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=z.ai&sz=64","catalogRank":400,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"z-ai-glm-4-5-air","name":"GLM 4.5 Air","provider":"Z.ai","family":null,"status":"active","variantType":"base","modelVersion":"z-ai/glm-4.5-air","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"131072","maxOutputTokens":"98304","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.13,"outputPrice":0.85,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://z.ai/"},"pricing":{"name":"Provider source","url":"https://z.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://z.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-coder","slug":"qwen-qwen3-coder","canonicalId":"qwen-qwen3-coder","name":"Qwen3 Coder 480B A35B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-coder-480b-a35b-07-25","modalities":["Text","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":3e-7,"completion":0.000001},"inputPrice":0.3,"outputPrice":1,"cachedInputPrice":null,"price":"$0.30","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":11.9,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":401,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-coder","name":"Qwen3 Coder 480B A35B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-coder-480b-a35b-07-25","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools"],"contextWindow":"262144","maxOutputTokens":"65536","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.3,"outputPrice":1,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"bytedance-ui-tars-1-5-7b","slug":"bytedance-ui-tars-1-5-7b","canonicalId":"bytedance-ui-tars-1-5-7b","name":"UI-TARS 7B","provider":"ByteDance","family":null,"status":"active","variantType":"base","modelVersion":"bytedance/ui-tars-1.5-7b","modalities":["Image","Text"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"2048","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":2e-7},"inputPrice":0.09999999999999999,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"pricing":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://seed.bytedance.com/","sourceUrl":"https://seed.bytedance.com/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=bytedance.com&sz=64","catalogRank":402,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"bytedance-ui-tars-1-5-7b","name":"UI-TARS 7B","provider":"ByteDance","family":null,"status":"active","variantType":"base","modelVersion":"bytedance/ui-tars-1.5-7b","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Image","Text"],"contextWindow":"128000","maxOutputTokens":"2048","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"pricing":{"name":"Provider source","url":"https://seed.bytedance.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://seed.bytedance.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-2-5-flash-lite","slug":"google-gemini-2-5-flash-lite","canonicalId":"google-gemini-2-5-flash-lite","name":"Gemini 2.5 Flash Lite","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-2.5-flash-lite","modalities":["Text","Image","File","Audio","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65535","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":4e-7},"inputPrice":0.09999999999999999,"outputPrice":0.39999999999999997,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":10.4,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":403,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-2-5-flash-lite","name":"Gemini 2.5 Flash Lite","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-2.5-flash-lite","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Audio","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65535","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.39999999999999997,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-2-5-flash-lite-batch","slug":"google-gemini-2-5-flash-lite-batch","canonicalId":"google-gemini-2-5-flash-lite-batch","name":"Gemini 2.5 Flash Lite (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-2.5-flash-lite","modalities":["Text","Image","File","Audio","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65535","apiAvailable":true,"pricing":{"prompt":5e-8,"completion":2e-7},"inputPrice":0.049999999999999996,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"price":"$0.05","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":10.4,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":404,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-2-5-flash-lite-batch","name":"Gemini 2.5 Flash Lite (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-2.5-flash-lite","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Audio","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65535","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.049999999999999996,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-235b-a22b-2507","slug":"qwen-qwen3-235b-a22b-2507","canonicalId":"qwen-qwen3-235b-a22b-2507","name":"Qwen3 235B A22B Instruct 2507","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-235b-a22b-07-25","modalities":["Text","Tools"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":9e-8,"completion":5.5e-7},"inputPrice":0.09,"outputPrice":0.55,"cachedInputPrice":null,"price":"$0.09","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":12,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":405,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-235b-a22b-2507","name":"Qwen3 235B A22B Instruct 2507","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-235b-a22b-07-25","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools"],"contextWindow":"262144","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.09,"outputPrice":0.55,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"moonshotai-kimi-k2","slug":"moonshotai-kimi-k2","canonicalId":"moonshotai-kimi-k2","name":"Kimi K2 0711","provider":"Moonshot AI","family":null,"status":"active","variantType":"base","modelVersion":"moonshotai/kimi-k2","modalities":["Text","Tools"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"98304","apiAvailable":true,"pricing":{"prompt":5.7e-7,"completion":0.0000023},"inputPrice":0.5700000000000001,"outputPrice":2.3,"cachedInputPrice":null,"price":"$0.57","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":12.7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://platform.moonshot.ai/docs/guide/models","catalogSourceUrl":"https://moonshot.ai/","sourceUrl":"https://platform.moonshot.ai/docs/guide/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=moonshot.ai&sz=64","catalogRank":406,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"moonshotai-kimi-k2","name":"Kimi K2 0711","provider":"Moonshot AI","family":null,"status":"active","variantType":"base","modelVersion":"moonshotai/kimi-k2","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools"],"contextWindow":"131072","maxOutputTokens":"98304","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.5700000000000001,"outputPrice":2.3,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://moonshot.ai/"},"pricing":{"name":"Provider source","url":"https://moonshot.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://moonshot.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"cognitivecomputations-dolphin-mistral-24b-venice-edition","slug":"cognitivecomputations-dolphin-mistral-24b-venice-edition","canonicalId":"cognitivecomputations-dolphin-mistral-24b-venice-edition","name":"Uncensored","provider":"Venice","family":null,"status":"active","variantType":"base","modelVersion":"venice/uncensored","modalities":["Text"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"8192","apiAvailable":true,"pricing":{"prompt":2e-7,"completion":9e-7},"inputPrice":0.19999999999999998,"outputPrice":0.8999999999999999,"cachedInputPrice":null,"price":"$0.20","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://venice.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://venice.ai/"},"pricing":{"name":"Provider source","url":"https://venice.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://venice.ai/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://venice.ai/","sourceUrl":"https://venice.ai/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=venice.ai&sz=64","catalogRank":407,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"cognitivecomputations-dolphin-mistral-24b-venice-edition","name":"Uncensored","provider":"Venice","family":null,"status":"active","variantType":"base","modelVersion":"venice/uncensored","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"128000","maxOutputTokens":"8192","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.19999999999999998,"outputPrice":0.8999999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://venice.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://venice.ai/"},"pricing":{"name":"Provider source","url":"https://venice.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://venice.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"tencent-hunyuan-a13b-instruct","slug":"tencent-hunyuan-a13b-instruct","canonicalId":"tencent-hunyuan-a13b-instruct","name":"Hunyuan A13B Instruct","provider":"Tencent","family":null,"status":"active","variantType":"base","modelVersion":"tencent/hunyuan-a13b-instruct","modalities":["Text","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"pricing":{"prompt":1.4e-7,"completion":5.7e-7},"inputPrice":0.14,"outputPrice":0.5700000000000001,"cachedInputPrice":null,"price":"$0.14","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"pricing":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"metrics":{},"fields":{}},"officialUrl":"https://cloud.tencent.com/product/hunyuan","catalogSourceUrl":"https://hunyuan.tencent.com/","sourceUrl":"https://cloud.tencent.com/product/hunyuan","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=tencent.com&sz=64","catalogRank":408,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"tencent-hunyuan-a13b-instruct","name":"Hunyuan A13B Instruct","provider":"Tencent","family":null,"status":"active","variantType":"base","modelVersion":"tencent/hunyuan-a13b-instruct","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Reasoning"],"contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.14,"outputPrice":0.5700000000000001,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"pricing":{"name":"Provider source","url":"https://hunyuan.tencent.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://hunyuan.tencent.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"morph-morph-v3-fast","slug":"morph-morph-v3-fast","canonicalId":"morph-morph-v3-fast","name":"Morph V3 Fast","provider":"Morph","family":null,"status":"active","variantType":"fast","modelVersion":"morph/morph-v3-fast","modalities":["Text"],"context_length":"81920","context":"81920","contextWindow":"81920","maxOutputTokens":"38000","apiAvailable":true,"pricing":{"prompt":8e-7,"completion":0.0000012},"inputPrice":0.7999999999999999,"outputPrice":1.2,"cachedInputPrice":null,"price":"$0.80","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":null,"catalogRank":409,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"morph-morph-v3-fast","name":"Morph V3 Fast","provider":"Morph","family":null,"status":"active","variantType":"fast","modelVersion":"morph/morph-v3-fast","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text"],"contextWindow":"81920","maxOutputTokens":"38000","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.7999999999999999,"outputPrice":1.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"morph-morph-v3-large","slug":"morph-morph-v3-large","canonicalId":"morph-morph-v3-large","name":"Morph V3 Large","provider":"Morph","family":null,"status":"active","variantType":"base","modelVersion":"morph/morph-v3-large","modalities":["Text"],"context_length":"262144","context":"262144","contextWindow":"262144","maxOutputTokens":"131072","apiAvailable":true,"pricing":{"prompt":9e-7,"completion":0.0000018999999999999998},"inputPrice":0.8999999999999999,"outputPrice":1.9,"cachedInputPrice":null,"price":"$0.90","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":null,"catalogRank":410,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"morph-morph-v3-large","name":"Morph V3 Large","provider":"Morph","family":null,"status":"active","variantType":"base","modelVersion":"morph/morph-v3-large","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text"],"contextWindow":"262144","maxOutputTokens":"131072","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.8999999999999999,"outputPrice":1.9,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-mistral-small-3-2-24b-instruct","slug":"mistralai-mistral-small-3-2-24b-instruct","canonicalId":"mistralai-mistral-small-3-2-24b-instruct","name":"Mistral Small 3.2 24B","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-small-3.2-24b-instruct-2506","modalities":["Image","Text","Tools"],"context_length":"256000","context":"256000","contextWindow":"256000","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":9.375e-8,"completion":2.5e-7},"inputPrice":0.09375,"outputPrice":0.25,"cachedInputPrice":null,"price":"$0.09","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":411,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-mistral-small-3-2-24b-instruct","name":"Mistral Small 3.2 24B","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-small-3.2-24b-instruct-2506","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Image","Text","Tools"],"contextWindow":"256000","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.09375,"outputPrice":0.25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-2-5-flash","slug":"google-gemini-2-5-flash","canonicalId":"google-gemini-2-5-flash","name":"Gemini 2.5 Flash","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-2.5-flash","modalities":["File","Image","Text","Audio","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65535","apiAvailable":true,"pricing":{"prompt":3e-7,"completion":0.0000025},"inputPrice":0.3,"outputPrice":2.5,"cachedInputPrice":null,"price":"$0.30","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":15.5,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":412,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-2-5-flash","name":"Gemini 2.5 Flash","provider":"Google","family":null,"status":"active","variantType":"fast","modelVersion":"google/gemini-2.5-flash","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Audio","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65535","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.3,"outputPrice":2.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-2-5-flash-batch","slug":"google-gemini-2-5-flash-batch","canonicalId":"google-gemini-2-5-flash-batch","name":"Gemini 2.5 Flash (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-2.5-flash","modalities":["File","Image","Text","Audio","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65535","apiAvailable":true,"pricing":{"prompt":1.5e-7,"completion":0.00000125},"inputPrice":0.15,"outputPrice":1.25,"cachedInputPrice":null,"price":"$0.15","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":15.5,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":413,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-2-5-flash-batch","name":"Gemini 2.5 Flash (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-2.5-flash","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Audio","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65535","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.15,"outputPrice":1.25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"gemini-2-5-pro","slug":"gemini-2-5-pro","canonicalId":"gemini-2-5-pro","name":"Gemini 2.5 Pro","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemini-2.5-pro","modalities":["Text","Image","File","Audio","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":0.00000125,"completion":0.00001},"inputPrice":1.25,"outputPrice":10,"cachedInputPrice":null,"price":"$1.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":16.1,"coding":33.3,"agents":1.6,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":414,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"gemini-2-5-pro","name":"Gemini 2.5 Pro","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemini-2.5-pro","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Audio","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.25,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-2-5-pro-batch","slug":"google-gemini-2-5-pro-batch","canonicalId":"google-gemini-2-5-pro-batch","name":"Gemini 2.5 Pro (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-2.5-pro","modalities":["Text","Image","File","Audio","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":6.25e-7,"completion":0.000005},"inputPrice":0.625,"outputPrice":5,"cachedInputPrice":null,"price":"$0.63","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":16.1,"coding":33.3,"agents":1.6,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":415,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-2-5-pro-batch","name":"Gemini 2.5 Pro (batch)","provider":"Google","family":null,"status":"active","variantType":"batch","modelVersion":"google/gemini-2.5-pro","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Audio","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.625,"outputPrice":5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"minimax-minimax-m1","slug":"minimax-minimax-m1","canonicalId":"minimax-minimax-m1","name":"MiniMax M1","provider":"MiniMax","family":null,"status":"active","variantType":"base","modelVersion":"minimax/minimax-m1","modalities":["Text","Tools","Reasoning"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"40000","apiAvailable":true,"pricing":{"prompt":5.5e-7,"completion":0.0000022},"inputPrice":0.55,"outputPrice":2.2,"cachedInputPrice":null,"price":"$0.55","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":11.7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}},"officialUrl":"https://platform.minimax.io/docs/guides/models","catalogSourceUrl":"https://minimax.io/","sourceUrl":"https://platform.minimax.io/docs/guides/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=minimax.io&sz=64","catalogRank":416,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"minimax-minimax-m1","name":"MiniMax M1","provider":"MiniMax","family":null,"status":"active","variantType":"base","modelVersion":"minimax/minimax-m1","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Tools","Reasoning"],"contextWindow":"1000000","maxOutputTokens":"40000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.55,"outputPrice":2.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-o3-pro","slug":"openai-o3-pro","canonicalId":"openai-o3-pro","name":"o3 Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/o3-pro-2025-06-10","modalities":["Text","File","Image","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"pricing":{"prompt":0.00002,"completion":0.00008},"inputPrice":20,"outputPrice":80,"cachedInputPrice":null,"price":"$20.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":21.9,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/o3-pro","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/o3-pro","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":417,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-o3-pro","name":"o3 Pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/o3-pro-2025-06-10","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","File","Image","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":20,"outputPrice":80,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-o3-pro-batch","slug":"openai-o3-pro-batch","canonicalId":"openai-o3-pro-batch","name":"o3 Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text","File","Image","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":0.00001,"completion":0.00004},"inputPrice":10,"outputPrice":40,"cachedInputPrice":null,"price":"$10.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://openai.com/","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://openai.com/","sourceUpdatedAt":{},"updated":"2026-08-27","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":418,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-o3-pro-batch","name":"o3 Pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","File","Image","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":null,"apiAvailable":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"inputPrice":10,"outputPrice":40,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-2-5-pro-preview","slug":"google-gemini-2-5-pro-preview","canonicalId":"google-gemini-2-5-pro-preview","name":"Gemini 2.5 Pro Preview 06-05","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/gemini-2.5-pro-preview-06-05","modalities":["File","Image","Text","Audio","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"pricing":{"prompt":0.00000125,"completion":0.00001},"inputPrice":1.25,"outputPrice":10,"cachedInputPrice":null,"price":"$1.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":419,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-2-5-pro-preview","name":"Gemini 2.5 Pro Preview 06-05","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/gemini-2.5-pro-preview-06-05","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["File","Image","Text","Audio","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65536","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.25,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-r1-0528","slug":"deepseek-deepseek-r1-0528","canonicalId":"deepseek-deepseek-r1-0528","name":"R1 0528","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"deepseek/deepseek-r1-0528","modalities":["Text","Tools","Reasoning"],"context_length":"163840","context":"163840","contextWindow":"163840","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":5e-7,"completion":0.00000215},"inputPrice":0.5,"outputPrice":2.1500000000000004,"cachedInputPrice":null,"price":"$0.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":13.1,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":420,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-r1-0528","name":"R1 0528","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"deepseek/deepseek-r1-0528","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"163840","maxOutputTokens":"32768","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.5,"outputPrice":2.1500000000000004,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-opus-4","slug":"anthropic-claude-opus-4","canonicalId":"anthropic-claude-opus-4","name":"Claude Opus 4","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4-opus-20250522","modalities":["Image","Text","File","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"32000","apiAvailable":true,"pricing":{"prompt":0.000015,"completion":0.000075},"inputPrice":15,"outputPrice":75,"cachedInputPrice":null,"price":"$15.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-09-21","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":421,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-opus-4","name":"Claude Opus 4","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4-opus-20250522","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text","File","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"32000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":15,"outputPrice":75,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"claude-sonnet-4","slug":"claude-sonnet-4","canonicalId":"claude-sonnet-4","name":"Claude Sonnet 4","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4-sonnet-20250522","modalities":["Image","Text","File","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"64000","apiAvailable":true,"pricing":{"prompt":0.000003,"completion":0.000015},"inputPrice":3,"outputPrice":15,"cachedInputPrice":null,"price":"$3.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":18.9,"coding":37.6,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":422,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"claude-sonnet-4","name":"Claude Sonnet 4","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-4-sonnet-20250522","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text","File","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"64000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":3,"outputPrice":15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemma-3n-e4b-it","slug":"google-gemma-3n-e4b-it","canonicalId":"google-gemma-3n-e4b-it","name":"Gemma 3n 4B","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text"],"context_length":"32768","context":"32768","contextWindow":"32768","maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":6e-8,"completion":1.2e-7},"inputPrice":0.06,"outputPrice":0.12,"cachedInputPrice":null,"price":"$0.06","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":0,"coding":3.2,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/","sourceUpdatedAt":{},"updated":"2026-08-25","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":423,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemma-3n-e4b-it","name":"Gemma 3n 4B","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text"],"contextWindow":"32768","maxOutputTokens":null,"apiAvailable":null,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"inputPrice":0.06,"outputPrice":0.12,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemini-2-5-pro-preview-05-06","slug":"google-gemini-2-5-pro-preview-05-06","canonicalId":"google-gemini-2-5-pro-preview-05-06","name":"Gemini 2.5 Pro Preview 05-06","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/gemini-2.5-pro-preview-03-25","modalities":["Text","Image","File","Audio","Video","Tools","Reasoning"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"65535","apiAvailable":true,"pricing":{"prompt":0.00000125,"completion":0.00001},"inputPrice":1.25,"outputPrice":10,"cachedInputPrice":null,"price":"$1.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-09-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":424,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemini-2-5-pro-preview-05-06","name":"Gemini 2.5 Pro Preview 05-06","provider":"Google","family":null,"status":"active","variantType":"preview","modelVersion":"google/gemini-2.5-pro-preview-03-25","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Audio","Video","Tools","Reasoning"],"contextWindow":"1048576","maxOutputTokens":"65535","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.25,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-mistral-medium-3","slug":"mistralai-mistral-medium-3","canonicalId":"mistralai-mistral-medium-3","name":"Mistral Medium 3","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-medium-3","modalities":["Text","Image","File","Tools"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"104857","apiAvailable":true,"pricing":{"prompt":4e-7,"completion":0.000002},"inputPrice":0.39999999999999997,"outputPrice":2,"cachedInputPrice":null,"price":"$0.40","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":9,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":425,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-mistral-medium-3","name":"Mistral Medium 3","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-medium-3","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools"],"contextWindow":"131072","maxOutputTokens":"104857","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.39999999999999997,"outputPrice":2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"arcee-ai-virtuoso-large","slug":"arcee-ai-virtuoso-large","canonicalId":"arcee-ai-virtuoso-large","name":"Virtuoso Large","provider":"Arcee AI","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text","Tools"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":7.5e-7,"completion":0.0000012},"inputPrice":0.75,"outputPrice":1.2,"cachedInputPrice":null,"price":"$0.75","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://arcee.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://arcee.ai/"},"pricing":{"name":"Provider source","url":"https://arcee.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://arcee.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://arcee.ai/","catalogSourceUrl":"https://arcee.ai/","sourceUrl":"https://arcee.ai/","sourceUpdatedAt":{},"updated":"2026-08-28","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=arcee.ai&sz=64","catalogRank":426,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"arcee-ai-virtuoso-large","name":"Virtuoso Large","provider":"Arcee AI","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Tools"],"contextWindow":"131072","maxOutputTokens":null,"apiAvailable":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"inputPrice":0.75,"outputPrice":1.2,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Provider source","url":"https://arcee.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://arcee.ai/"},"pricing":{"name":"Provider source","url":"https://arcee.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://arcee.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"meta-llama-llama-guard-4-12b","slug":"meta-llama-llama-guard-4-12b","canonicalId":"meta-llama-llama-guard-4-12b","name":"Llama Guard 4 12B","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta-llama/llama-guard-4-12b","modalities":["Image","Text"],"context_length":"163840","context":"163840","contextWindow":"163840","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":1.8e-7,"completion":1.8e-7},"inputPrice":0.18,"outputPrice":0.18,"cachedInputPrice":null,"price":"$0.18","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}},"officialUrl":"https://www.llama.com/models/","catalogSourceUrl":"https://ai.meta.com/","sourceUrl":"https://www.llama.com/models/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=meta.com&sz=64","catalogRank":427,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"meta-llama-llama-guard-4-12b","name":"Llama Guard 4 12B","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta-llama/llama-guard-4-12b","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Image","Text"],"contextWindow":"163840","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.18,"outputPrice":0.18,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-14b","slug":"qwen-qwen3-14b","canonicalId":"qwen-qwen3-14b","name":"Qwen3 14B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-14b-04-28","modalities":["Text","Tools","Reasoning"],"context_length":"40960","context":"40960","contextWindow":"40960","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":1.2e-7,"completion":2.4e-7},"inputPrice":0.12,"outputPrice":0.24,"cachedInputPrice":null,"price":"$0.12","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":8.2,"coding":13.8,"agents":0.9,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":428,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-14b","name":"Qwen3 14B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-14b-04-28","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"40960","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.12,"outputPrice":0.24,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-30b-a3b","slug":"qwen-qwen3-30b-a3b","canonicalId":"qwen-qwen3-30b-a3b","name":"Qwen3 30B A3B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-30b-a3b-04-28","modalities":["Text","Tools","Reasoning"],"context_length":"40960","context":"40960","contextWindow":"40960","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":1.2e-7,"completion":5e-7},"inputPrice":0.12,"outputPrice":0.5,"cachedInputPrice":null,"price":"$0.12","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":429,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-30b-a3b","name":"Qwen3 30B A3B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-30b-a3b-04-28","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"40960","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.12,"outputPrice":0.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen3-32b","slug":"qwen-qwen3-32b","canonicalId":"qwen-qwen3-32b","name":"Qwen3 32B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-32b-04-28","modalities":["Text","Tools","Reasoning"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":8e-8,"completion":2.8e-7},"inputPrice":0.08,"outputPrice":0.28,"cachedInputPrice":null,"price":"$0.08","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":8.6,"coding":15.3,"agents":0.9,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":430,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen3-32b","name":"Qwen3 32B","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen3-32b-04-28","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools","Reasoning"],"contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.08,"outputPrice":0.28,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"o3","slug":"o3","canonicalId":"o3","name":"o3","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/o3-2025-04-16","modalities":["Image","Text","File","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000008},"inputPrice":2,"outputPrice":8,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":20.2,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/o3","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/o3","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":431,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"o3","name":"o3","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/o3-2025-04-16","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text","File","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":8,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-o3-batch","slug":"openai-o3-batch","canonicalId":"openai-o3-batch","name":"o3 (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/o3-2025-04-16","modalities":["Image","Text","File","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000004},"inputPrice":1,"outputPrice":4,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":20.2,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/o3:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/o3:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":432,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-o3-batch","name":"o3 (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/o3-2025-04-16","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text","File","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":4,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-o4-mini","slug":"openai-o4-mini","canonicalId":"openai-o4-mini","name":"o4 Mini","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/o4-mini-2025-04-16","modalities":["Image","Text","File","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"pricing":{"prompt":0.0000011,"completion":0.0000044},"inputPrice":1.1,"outputPrice":4.4,"cachedInputPrice":null,"price":"$1.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":16.7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/o4-mini","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/o4-mini","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":433,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-o4-mini","name":"o4 Mini","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/o4-mini-2025-04-16","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text","File","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.1,"outputPrice":4.4,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-o4-mini-batch","slug":"openai-o4-mini-batch","canonicalId":"openai-o4-mini-batch","name":"o4 Mini (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/o4-mini-2025-04-16","modalities":["Image","Text","File","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"pricing":{"prompt":5.5e-7,"completion":0.0000022},"inputPrice":0.55,"outputPrice":2.2,"cachedInputPrice":null,"price":"$0.55","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":16.7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/o4-mini:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/o4-mini:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":434,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-o4-mini-batch","name":"o4 Mini (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/o4-mini-2025-04-16","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text","File","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.55,"outputPrice":2.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-o4-mini-high","slug":"openai-o4-mini-high","canonicalId":"openai-o4-mini-high","name":"o4 Mini High","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/o4-mini-high-2025-04-16","modalities":["Image","Text","File","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"pricing":{"prompt":0.0000011,"completion":0.0000044},"inputPrice":1.1,"outputPrice":4.4,"cachedInputPrice":null,"price":"$1.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/o4-mini-high","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/o4-mini-high","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":435,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-o4-mini-high","name":"o4 Mini High","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/o4-mini-high-2025-04-16","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text","File","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.1,"outputPrice":4.4,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-o4-mini-high-batch","slug":"openai-o4-mini-high-batch","canonicalId":"openai-o4-mini-high-batch","name":"o4 Mini High (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Image","Text","File","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":5.5e-7,"completion":0.0000022},"inputPrice":0.55,"outputPrice":2.2,"cachedInputPrice":null,"price":"$0.55","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://openai.com/","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://openai.com/","sourceUpdatedAt":{},"updated":"2026-08-27","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":436,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-o4-mini-high-batch","name":"o4 Mini High (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Image","Text","File","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":null,"apiAvailable":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"inputPrice":0.55,"outputPrice":2.2,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-4-1","slug":"openai-gpt-4-1","canonicalId":"openai-gpt-4-1","name":"GPT-4.1","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-4.1-2025-04-14","modalities":["Image","Text","File","Tools"],"context_length":"1047576","context":"1047576","contextWindow":"1047576","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000008},"inputPrice":2,"outputPrice":8,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":12.7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-4.1","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-4.1","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":437,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-4-1","name":"GPT-4.1","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-4.1-2025-04-14","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text","File","Tools"],"contextWindow":"1047576","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":8,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-4-1-batch","slug":"openai-gpt-4-1-batch","canonicalId":"openai-gpt-4-1-batch","name":"GPT-4.1 (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-4.1-2025-04-14","modalities":["Image","Text","File","Tools"],"context_length":"1047576","context":"1047576","contextWindow":"1047576","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000004},"inputPrice":1,"outputPrice":4,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":12.7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-4.1:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-4.1:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":438,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-4-1-batch","name":"GPT-4.1 (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-4.1-2025-04-14","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text","File","Tools"],"contextWindow":"1047576","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":1,"outputPrice":4,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-4-1-mini","slug":"openai-gpt-4-1-mini","canonicalId":"openai-gpt-4-1-mini","name":"GPT-4.1 Mini","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/gpt-4.1-mini-2025-04-14","modalities":["Image","Text","File","Tools"],"context_length":"1047576","context":"1047576","contextWindow":"1047576","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":4e-7,"completion":0.0000016},"inputPrice":0.39999999999999997,"outputPrice":1.5999999999999999,"cachedInputPrice":null,"price":"$0.40","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":10.2,"coding":20.2,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-4.1-mini","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-4.1-mini","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":439,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-4-1-mini","name":"GPT-4.1 Mini","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/gpt-4.1-mini-2025-04-14","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text","File","Tools"],"contextWindow":"1047576","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.39999999999999997,"outputPrice":1.5999999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-4-1-mini-batch","slug":"openai-gpt-4-1-mini-batch","canonicalId":"openai-gpt-4-1-mini-batch","name":"GPT-4.1 Mini (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-4.1-mini-2025-04-14","modalities":["Image","Text","File","Tools"],"context_length":"1047576","context":"1047576","contextWindow":"1047576","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":2e-7,"completion":8e-7},"inputPrice":0.19999999999999998,"outputPrice":0.7999999999999999,"cachedInputPrice":null,"price":"$0.20","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":10.2,"coding":20.2,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-4.1-mini:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-4.1-mini:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":440,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-4-1-mini-batch","name":"GPT-4.1 Mini (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-4.1-mini-2025-04-14","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text","File","Tools"],"contextWindow":"1047576","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.19999999999999998,"outputPrice":0.7999999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-4-1-nano","slug":"openai-gpt-4-1-nano","canonicalId":"openai-gpt-4-1-nano","name":"GPT-4.1 Nano","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-4.1-nano-2025-04-14","modalities":["Image","Text","File","Tools"],"context_length":"1047576","context":"1047576","contextWindow":"1047576","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":4e-7},"inputPrice":0.09999999999999999,"outputPrice":0.39999999999999997,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7.8,"coding":11.1,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-4.1-nano","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-4.1-nano","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":441,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-4-1-nano","name":"GPT-4.1 Nano","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-4.1-nano-2025-04-14","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text","File","Tools"],"contextWindow":"1047576","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.39999999999999997,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-4-1-nano-batch","slug":"openai-gpt-4-1-nano-batch","canonicalId":"openai-gpt-4-1-nano-batch","name":"GPT-4.1 Nano (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-4.1-nano-2025-04-14","modalities":["Image","Text","File","Tools"],"context_length":"1047576","context":"1047576","contextWindow":"1047576","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":5e-8,"completion":2e-7},"inputPrice":0.049999999999999996,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"price":"$0.05","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7.8,"coding":11.1,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-4.1-nano:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-4.1-nano:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":442,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-4-1-nano-batch","name":"GPT-4.1 Nano (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-4.1-nano-2025-04-14","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Image","Text","File","Tools"],"contextWindow":"1047576","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.049999999999999996,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"meta-llama-llama-4-maverick","slug":"meta-llama-llama-4-maverick","canonicalId":"meta-llama-llama-4-maverick","name":"Llama 4 Maverick","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta-llama/llama-4-maverick-17b-128e-instruct","modalities":["Text","Image","Tools"],"context_length":"1048576","context":"1048576","contextWindow":"1048576","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":1.875e-7,"completion":6.525e-7},"inputPrice":0.1875,"outputPrice":0.6525,"cachedInputPrice":null,"price":"$0.19","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":10,"coding":16.3,"agents":0.6,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}},"officialUrl":"https://www.llama.com/models/","catalogSourceUrl":"https://ai.meta.com/","sourceUrl":"https://www.llama.com/models/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=meta.com&sz=64","catalogRank":443,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"meta-llama-llama-4-maverick","name":"Llama 4 Maverick","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta-llama/llama-4-maverick-17b-128e-instruct","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Image","Tools"],"contextWindow":"1048576","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.1875,"outputPrice":0.6525,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"meta-llama-llama-4-scout","slug":"meta-llama-llama-4-scout","canonicalId":"meta-llama-llama-4-scout","name":"Llama 4 Scout","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta-llama/llama-4-scout-17b-16e-instruct","modalities":["Text","Image","Tools"],"context_length":"1310720","context":"1310720","contextWindow":"1310720","maxOutputTokens":"117964","apiAvailable":true,"pricing":{"prompt":1.8e-7,"completion":5.9e-7},"inputPrice":0.18,"outputPrice":0.59,"cachedInputPrice":null,"price":"$0.18","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":8.1,"coding":8.2,"agents":0.5,"speed":2600,"latency":330,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}},"officialUrl":"https://www.llama.com/models/","catalogSourceUrl":"https://ai.meta.com/","sourceUrl":"https://www.llama.com/models/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=meta.com&sz=64","catalogRank":444,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"meta-llama-llama-4-scout","name":"Llama 4 Scout","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta-llama/llama-4-scout-17b-16e-instruct","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Image","Tools"],"contextWindow":"1310720","maxOutputTokens":"117964","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.18,"outputPrice":0.59,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-chat-v3-0324","slug":"deepseek-deepseek-chat-v3-0324","canonicalId":"deepseek-deepseek-chat-v3-0324","name":"DeepSeek V3 0324","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"deepseek/deepseek-chat-v3-0324","modalities":["Text","Tools"],"context_length":"163840","context":"163840","contextWindow":"163840","maxOutputTokens":"115200","apiAvailable":true,"pricing":{"prompt":2.9e-7,"completion":0.00000114},"inputPrice":0.29,"outputPrice":1.1400000000000001,"cachedInputPrice":null,"price":"$0.29","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":9.7,"coding":21.2,"agents":0.8,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":445,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-chat-v3-0324","name":"DeepSeek V3 0324","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"deepseek/deepseek-chat-v3-0324","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools"],"contextWindow":"163840","maxOutputTokens":"115200","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.29,"outputPrice":1.1400000000000001,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-o1-pro","slug":"openai-o1-pro","canonicalId":"openai-o1-pro","name":"o1-pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/o1-pro","modalities":["Text","Image","File","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"pricing":{"prompt":0.00015,"completion":0.0006},"inputPrice":150,"outputPrice":600,"cachedInputPrice":null,"price":"$150.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":12.4,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/o1-pro","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/o1-pro","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":446,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-o1-pro","name":"o1-pro","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/o1-pro","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Reasoning"],"contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":150,"outputPrice":600,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-o1-pro-batch","slug":"openai-o1-pro-batch","canonicalId":"openai-o1-pro-batch","name":"o1-pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text","Image","File","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":0.000075,"completion":0.0003},"inputPrice":75,"outputPrice":300,"cachedInputPrice":null,"price":"$75.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://openai.com/","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://openai.com/","sourceUpdatedAt":{},"updated":"2026-08-27","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":447,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-o1-pro-batch","name":"o1-pro (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Reasoning"],"contextWindow":"200000","maxOutputTokens":null,"apiAvailable":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"inputPrice":75,"outputPrice":300,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-mistral-small-3-1-24b-instruct","slug":"mistralai-mistral-small-3-1-24b-instruct","canonicalId":"mistralai-mistral-small-3-1-24b-instruct","name":"Mistral Small 3.1 24B","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-small-3.1-24b-instruct-2503","modalities":["Text","Image","Tools"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"102400","apiAvailable":true,"pricing":{"prompt":3.5099999999999995e-7,"completion":5.55e-7},"inputPrice":0.351,"outputPrice":0.5549999999999999,"cachedInputPrice":null,"price":"$0.35","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":448,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-mistral-small-3-1-24b-instruct","name":"Mistral Small 3.1 24B","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-small-3.1-24b-instruct-2503","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Image","Tools"],"contextWindow":"128000","maxOutputTokens":"102400","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.351,"outputPrice":0.5549999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"cohere-command-a","slug":"cohere-command-a","canonicalId":"cohere-command-a","name":"Command A","provider":"Cohere","family":null,"status":"active","variantType":"base","modelVersion":"cohere/command-a-03-2025","modalities":["Text"],"context_length":"256000","context":"256000","contextWindow":"256000","maxOutputTokens":"8192","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.00001},"inputPrice":2.5,"outputPrice":10,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":13.1,"coding":27.8,"agents":1,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://cohere.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://cohere.com/"},"pricing":{"name":"Provider source","url":"https://cohere.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://cohere.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.cohere.com/docs/models","catalogSourceUrl":"https://cohere.com/","sourceUrl":"https://docs.cohere.com/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=cohere.com&sz=64","catalogRank":449,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"cohere-command-a","name":"Command A","provider":"Cohere","family":null,"status":"active","variantType":"base","modelVersion":"cohere/command-a-03-2025","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"256000","maxOutputTokens":"8192","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":2.5,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://cohere.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://cohere.com/"},"pricing":{"name":"Provider source","url":"https://cohere.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://cohere.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemma-3-12b-it","slug":"google-gemma-3-12b-it","canonicalId":"google-gemma-3-12b-it","name":"Gemma 3 12B","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemma-3-12b-it","modalities":["Text","Image","Tools"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":5e-8,"completion":1.5e-7},"inputPrice":0.049999999999999996,"outputPrice":0.15,"cachedInputPrice":null,"price":"$0.05","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":3.8,"coding":5.8,"agents":0.1,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":450,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemma-3-12b-it","name":"Gemma 3 12B","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemma-3-12b-it","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Image","Tools"],"contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.049999999999999996,"outputPrice":0.15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemma-3-4b-it","slug":"google-gemma-3-4b-it","canonicalId":"google-gemma-3-4b-it","name":"Gemma 3 4B","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemma-3-4b-it","modalities":["Text","Image"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":5e-8,"completion":1e-7},"inputPrice":0.049999999999999996,"outputPrice":0.09999999999999999,"cachedInputPrice":null,"price":"$0.05","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":4.8,"coding":2.7,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":451,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemma-3-4b-it","name":"Gemma 3 4B","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemma-3-4b-it","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Image"],"contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.049999999999999996,"outputPrice":0.09999999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemma-3-27b-it","slug":"google-gemma-3-27b-it","canonicalId":"google-gemma-3-27b-it","name":"Gemma 3 27B","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemma-3-27b-it","modalities":["Text","Image","Tools"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"pricing":{"prompt":8e-8,"completion":4.5e-7},"inputPrice":0.08,"outputPrice":0.44999999999999996,"cachedInputPrice":null,"price":"$0.08","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":4.9,"coding":10.1,"agents":0.1,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":452,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemma-3-27b-it","name":"Gemma 3 27B","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemma-3-27b-it","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Image","Tools"],"contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.08,"outputPrice":0.44999999999999996,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"rekaai-reka-flash-3","slug":"rekaai-reka-flash-3","canonicalId":"rekaai-reka-flash-3","name":"Reka Flash 3","provider":"Rekaai","family":null,"status":"active","variantType":"fast","modelVersion":"rekaai/reka-flash-3","modalities":["Text","Reasoning"],"context_length":"65536","context":"65536","contextWindow":"65536","maxOutputTokens":"58982","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":2e-7},"inputPrice":0.09999999999999999,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":6.4,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://reka.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://reka.ai/"},"pricing":{"name":"Provider source","url":"https://reka.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://reka.ai/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://reka.ai/","sourceUrl":"https://reka.ai/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=reka.ai&sz=64","catalogRank":453,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"rekaai-reka-flash-3","name":"Reka Flash 3","provider":"Rekaai","family":null,"status":"active","variantType":"fast","modelVersion":"rekaai/reka-flash-3","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Reasoning"],"contextWindow":"65536","maxOutputTokens":"58982","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://reka.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://reka.ai/"},"pricing":{"name":"Provider source","url":"https://reka.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://reka.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"thedrummer-skyfall-36b-v2","slug":"thedrummer-skyfall-36b-v2","canonicalId":"thedrummer-skyfall-36b-v2","name":"Skyfall 36B V2","provider":"TheDrummer","family":null,"status":"active","variantType":"base","modelVersion":"thedrummer/skyfall-36b-v2","modalities":["Text"],"context_length":"32768","context":"32768","contextWindow":"32768","maxOutputTokens":"29491","apiAvailable":true,"pricing":{"prompt":5.5e-7,"completion":8e-7},"inputPrice":0.55,"outputPrice":0.7999999999999999,"cachedInputPrice":null,"price":"$0.55","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":454,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"thedrummer-skyfall-36b-v2","name":"Skyfall 36B V2","provider":"TheDrummer","family":null,"status":"active","variantType":"base","modelVersion":"thedrummer/skyfall-36b-v2","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"32768","maxOutputTokens":"29491","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.55,"outputPrice":0.7999999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"perplexity-sonar-deep-research","slug":"perplexity-sonar-deep-research","canonicalId":"perplexity-sonar-deep-research","name":"Sonar Deep Research","provider":"Perplexity","family":null,"status":"active","variantType":"base","modelVersion":"perplexity/sonar-deep-research","modalities":["Text","Reasoning"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"115200","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000008},"inputPrice":2,"outputPrice":8,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://perplexity.ai/"},"pricing":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://perplexity.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.perplexity.ai/getting-started/models","catalogSourceUrl":"https://perplexity.ai/","sourceUrl":"https://docs.perplexity.ai/getting-started/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":true,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=perplexity.ai&sz=64","catalogRank":455,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"perplexity-sonar-deep-research","name":"Sonar Deep Research","provider":"Perplexity","family":null,"status":"active","variantType":"base","modelVersion":"perplexity/sonar-deep-research","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Reasoning"],"contextWindow":"128000","maxOutputTokens":"115200","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":true,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":2,"outputPrice":8,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://perplexity.ai/"},"pricing":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://perplexity.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"perplexity-sonar-pro","slug":"perplexity-sonar-pro","canonicalId":"perplexity-sonar-pro","name":"Sonar Pro","provider":"Perplexity","family":null,"status":"active","variantType":"base","modelVersion":"perplexity/sonar-pro","modalities":["Text","Image"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"8000","apiAvailable":true,"pricing":{"prompt":0.000003,"completion":0.000015},"inputPrice":3,"outputPrice":15,"cachedInputPrice":null,"price":"$3.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://perplexity.ai/"},"pricing":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://perplexity.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.perplexity.ai/getting-started/models","catalogSourceUrl":"https://perplexity.ai/","sourceUrl":"https://docs.perplexity.ai/getting-started/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":true,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=perplexity.ai&sz=64","catalogRank":456,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"perplexity-sonar-pro","name":"Sonar Pro","provider":"Perplexity","family":null,"status":"active","variantType":"base","modelVersion":"perplexity/sonar-pro","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image"],"contextWindow":"200000","maxOutputTokens":"8000","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":true,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":3,"outputPrice":15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://perplexity.ai/"},"pricing":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://perplexity.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"perplexity-sonar-reasoning-pro","slug":"perplexity-sonar-reasoning-pro","canonicalId":"perplexity-sonar-reasoning-pro","name":"Sonar Reasoning Pro","provider":"Perplexity","family":null,"status":"active","variantType":"base","modelVersion":"perplexity/sonar-reasoning-pro","modalities":["Text","Image","Reasoning"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"115200","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000008},"inputPrice":2,"outputPrice":8,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":11.8,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://perplexity.ai/"},"pricing":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://perplexity.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.perplexity.ai/getting-started/models","catalogSourceUrl":"https://perplexity.ai/","sourceUrl":"https://docs.perplexity.ai/getting-started/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":true,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=perplexity.ai&sz=64","catalogRank":457,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"perplexity-sonar-reasoning-pro","name":"Sonar Reasoning Pro","provider":"Perplexity","family":null,"status":"active","variantType":"base","modelVersion":"perplexity/sonar-reasoning-pro","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Reasoning"],"contextWindow":"128000","maxOutputTokens":"115200","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":true,"reasoningCapability":true,"promptCaching":false,"fineTuning":false,"inputPrice":2,"outputPrice":8,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://perplexity.ai/"},"pricing":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://perplexity.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-mistral-saba","slug":"mistralai-mistral-saba","canonicalId":"mistralai-mistral-saba","name":"Saba","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-saba-2502","modalities":["Text","File","Tools"],"context_length":"32768","context":"32768","contextWindow":"32768","maxOutputTokens":"26214","apiAvailable":true,"pricing":{"prompt":2e-7,"completion":6e-7},"inputPrice":0.19999999999999998,"outputPrice":0.6,"cachedInputPrice":null,"price":"$0.20","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":6.5,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":458,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-mistral-saba","name":"Saba","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-saba-2502","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","File","Tools"],"contextWindow":"32768","maxOutputTokens":"26214","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.19999999999999998,"outputPrice":0.6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-o3-mini-high","slug":"openai-o3-mini-high","canonicalId":"openai-o3-mini-high","name":"o3 Mini High","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/o3-mini-high-2025-01-31","modalities":["Text","File","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"pricing":{"prompt":0.0000011,"completion":0.0000044},"inputPrice":1.1,"outputPrice":4.4,"cachedInputPrice":null,"price":"$1.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":11,"coding":16.3,"agents":0.9,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/o3-mini-high","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/o3-mini-high","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":459,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-o3-mini-high","name":"o3 Mini High","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/o3-mini-high-2025-01-31","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","File","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.1,"outputPrice":4.4,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-o3-mini-high-batch","slug":"openai-o3-mini-high-batch","canonicalId":"openai-o3-mini-high-batch","name":"o3 Mini High (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text","File","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":5.5e-7,"completion":0.0000022},"inputPrice":0.55,"outputPrice":2.2,"cachedInputPrice":null,"price":"$0.55","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":15.7,"coding":16.3,"agents":1.7,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://openai.com/","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://openai.com/","sourceUpdatedAt":{},"updated":"2026-08-27","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":460,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-o3-mini-high-batch","name":"o3 Mini High (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","File","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":null,"apiAvailable":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"inputPrice":0.55,"outputPrice":2.2,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"aion-labs-aion-rp-llama-3-1-8b","slug":"aion-labs-aion-rp-llama-3-1-8b","canonicalId":"aion-labs-aion-rp-llama-3-1-8b","name":"Aion-RP 1.0 (8B)","provider":"AionLabs","family":null,"status":"active","variantType":"base","modelVersion":"aion-labs/aion-rp-llama-3.1-8b","modalities":["Text"],"context_length":"32768","context":"32768","contextWindow":"32768","maxOutputTokens":"29491","apiAvailable":true,"pricing":{"prompt":8e-7,"completion":0.0000016},"inputPrice":0.7999999999999999,"outputPrice":1.5999999999999999,"cachedInputPrice":null,"price":"$0.80","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aionlabs.ai/"},"pricing":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aionlabs.ai/"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"https://aionlabs.ai/","sourceUrl":"https://aionlabs.ai/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=aionlabs.ai&sz=64","catalogRank":461,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"aion-labs-aion-rp-llama-3-1-8b","name":"Aion-RP 1.0 (8B)","provider":"AionLabs","family":null,"status":"active","variantType":"base","modelVersion":"aion-labs/aion-rp-llama-3.1-8b","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text"],"contextWindow":"32768","maxOutputTokens":"29491","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.7999999999999999,"outputPrice":1.5999999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aionlabs.ai/"},"pricing":{"name":"Provider source","url":"https://aionlabs.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aionlabs.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen-plus","slug":"qwen-qwen-plus","canonicalId":"qwen-qwen-plus","name":"Qwen-Plus","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen-plus-2025-01-25","modalities":["Text","Tools"],"context_length":"1000000","context":"1000000","contextWindow":"1000000","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":2.6e-7,"completion":7.8e-7},"inputPrice":0.26,"outputPrice":0.78,"cachedInputPrice":null,"price":"$0.26","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":462,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen-plus","name":"Qwen-Plus","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen-plus-2025-01-25","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Tools"],"contextWindow":"1000000","maxOutputTokens":"32768","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.26,"outputPrice":0.78,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen2-5-vl-72b-instruct","slug":"qwen-qwen2-5-vl-72b-instruct","canonicalId":"qwen-qwen2-5-vl-72b-instruct","name":"Qwen2.5 VL 72B Instruct","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen2.5-vl-72b-instruct","modalities":["Text","Image"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"115200","apiAvailable":true,"pricing":{"prompt":8e-7,"completion":0.000001},"inputPrice":0.7999999999999999,"outputPrice":1,"cachedInputPrice":null,"price":"$0.80","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":463,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen2-5-vl-72b-instruct","name":"Qwen2.5 VL 72B Instruct","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen2.5-vl-72b-instruct","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Image"],"contextWindow":"128000","maxOutputTokens":"115200","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.7999999999999999,"outputPrice":1,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-o3-mini","slug":"openai-o3-mini","canonicalId":"openai-o3-mini","name":"o3 Mini","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/o3-mini-2025-01-31","modalities":["Text","File","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"pricing":{"prompt":0.0000011,"completion":0.0000044},"inputPrice":1.1,"outputPrice":4.4,"cachedInputPrice":null,"price":"$1.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":12.5,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/o3-mini","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/o3-mini","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":464,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-o3-mini","name":"o3 Mini","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/o3-mini-2025-01-31","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","File","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":1.1,"outputPrice":4.4,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-o3-mini-batch","slug":"openai-o3-mini-batch","canonicalId":"openai-o3-mini-batch","name":"o3 Mini (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/o3-mini-2025-01-31","modalities":["Text","File","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"pricing":{"prompt":5.5e-7,"completion":0.0000022},"inputPrice":0.55,"outputPrice":2.2,"cachedInputPrice":null,"price":"$0.55","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":12.5,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/o3-mini:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/o3-mini:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":465,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-o3-mini-batch","name":"o3 Mini (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/o3-mini-2025-01-31","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","File","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":0.55,"outputPrice":2.2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-mistral-small-24b-instruct-2501","slug":"mistralai-mistral-small-24b-instruct-2501","canonicalId":"mistralai-mistral-small-24b-instruct-2501","name":"Mistral Small 3","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-small-24b-instruct-2501","modalities":["Text"],"context_length":"32768","context":"32768","contextWindow":"32768","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":5e-8,"completion":8e-8},"inputPrice":0.049999999999999996,"outputPrice":0.08,"cachedInputPrice":null,"price":"$0.05","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":6.7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":466,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-mistral-small-24b-instruct-2501","name":"Mistral Small 3","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-small-24b-instruct-2501","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"32768","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.049999999999999996,"outputPrice":0.08,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"perplexity-sonar","slug":"perplexity-sonar","canonicalId":"perplexity-sonar","name":"Sonar","provider":"Perplexity","family":null,"status":"active","variantType":"base","modelVersion":"perplexity/sonar","modalities":["Text","Image"],"context_length":"127072","context":"127072","contextWindow":"127072","maxOutputTokens":"114364","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000001},"inputPrice":1,"outputPrice":1,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7.7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://perplexity.ai/"},"pricing":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://perplexity.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.perplexity.ai/getting-started/models","catalogSourceUrl":"https://perplexity.ai/","sourceUrl":"https://docs.perplexity.ai/getting-started/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":true,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=perplexity.ai&sz=64","catalogRank":467,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"perplexity-sonar","name":"Sonar","provider":"Perplexity","family":null,"status":"active","variantType":"base","modelVersion":"perplexity/sonar","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image"],"contextWindow":"127072","maxOutputTokens":"114364","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":true,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":1,"outputPrice":1,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://perplexity.ai/"},"pricing":{"name":"Provider source","url":"https://perplexity.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://perplexity.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"minimax-minimax-01","slug":"minimax-minimax-01","canonicalId":"minimax-minimax-01","name":"MiniMax-01","provider":"MiniMax","family":null,"status":"active","variantType":"base","modelVersion":"minimax/minimax-01","modalities":["Text","Image"],"context_length":"1000192","context":"1000192","contextWindow":"1000192","maxOutputTokens":"900172","apiAvailable":true,"pricing":{"prompt":2e-7,"completion":0.0000011},"inputPrice":0.19999999999999998,"outputPrice":1.1,"cachedInputPrice":null,"price":"$0.20","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}},"officialUrl":"https://platform.minimax.io/docs/guides/models","catalogSourceUrl":"https://minimax.io/","sourceUrl":"https://platform.minimax.io/docs/guides/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=minimax.io&sz=64","catalogRank":468,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"minimax-minimax-01","name":"MiniMax-01","provider":"MiniMax","family":null,"status":"active","variantType":"base","modelVersion":"minimax/minimax-01","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Image"],"contextWindow":"1000192","maxOutputTokens":"900172","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.19999999999999998,"outputPrice":1.1,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://minimax.io/"},"pricing":{"name":"Provider source","url":"https://minimax.io/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://minimax.io/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"microsoft-phi-4","slug":"microsoft-phi-4","canonicalId":"microsoft-phi-4","name":"Phi 4","provider":"Microsoft","family":null,"status":"active","variantType":"base","modelVersion":"microsoft/phi-4","modalities":["Text"],"context_length":"16384","context":"16384","contextWindow":"16384","maxOutputTokens":"14745","apiAvailable":true,"pricing":{"prompt":7e-8,"completion":1.4e-7},"inputPrice":0.07,"outputPrice":0.14,"cachedInputPrice":null,"price":"$0.07","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":5.9,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://microsoft.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://microsoft.com/"},"pricing":{"name":"Provider source","url":"https://microsoft.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://microsoft.com/"},"metrics":{},"fields":{}},"officialUrl":"https://azure.microsoft.com/en-us/products/ai-services/ai-model-catalog","catalogSourceUrl":"https://microsoft.com/","sourceUrl":"https://azure.microsoft.com/en-us/products/ai-services/ai-model-catalog","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=microsoft.com&sz=64","catalogRank":469,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"microsoft-phi-4","name":"Phi 4","provider":"Microsoft","family":null,"status":"active","variantType":"base","modelVersion":"microsoft/phi-4","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"16384","maxOutputTokens":"14745","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.07,"outputPrice":0.14,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://microsoft.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://microsoft.com/"},"pricing":{"name":"Provider source","url":"https://microsoft.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://microsoft.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"deepseek-deepseek-chat","slug":"deepseek-deepseek-chat","canonicalId":"deepseek-deepseek-chat","name":"DeepSeek V3","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"deepseek/deepseek-chat-v3","modalities":["Text","Tools"],"context_length":"163840","context":"163840","contextWindow":"163840","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":3.2e-7,"completion":8.9e-7},"inputPrice":0.32,"outputPrice":0.8899999999999999,"cachedInputPrice":null,"price":"$0.32","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}},"officialUrl":"https://api-docs.deepseek.com/quick_start/pricing","catalogSourceUrl":"https://api-docs.deepseek.com/","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=deepseek.com&sz=64","catalogRank":470,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"deepseek-deepseek-chat","name":"DeepSeek V3","provider":"DeepSeek","family":null,"status":"active","variantType":"base","modelVersion":"deepseek/deepseek-chat-v3","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools"],"contextWindow":"163840","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.32,"outputPrice":0.8899999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"pricing":{"name":"Provider source","url":"https://api-docs.deepseek.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://api-docs.deepseek.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"sao10k-l3-3-euryale-70b","slug":"sao10k-l3-3-euryale-70b","canonicalId":"sao10k-l3-3-euryale-70b","name":"Llama 3.3 Euryale 70B","provider":"Sao10K","family":null,"status":"active","variantType":"base","modelVersion":"sao10k/l3.3-euryale-70b-v2.3","modalities":["Text"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":6.5e-7,"completion":7.5e-7},"inputPrice":0.65,"outputPrice":0.75,"cachedInputPrice":null,"price":"$0.65","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":471,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"sao10k-l3-3-euryale-70b","name":"Llama 3.3 Euryale 70B","provider":"Sao10K","family":null,"status":"active","variantType":"base","modelVersion":"sao10k/l3.3-euryale-70b-v2.3","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.65,"outputPrice":0.75,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-o1","slug":"openai-o1","canonicalId":"openai-o1","name":"o1","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/o1-2024-12-17","modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"pricing":{"prompt":0.000015,"completion":0.00006},"inputPrice":15,"outputPrice":60,"cachedInputPrice":null,"price":"$15.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":15.2,"coding":39.7,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/o1","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/o1","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":472,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-o1","name":"o1","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/o1-2024-12-17","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":"100000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":true,"promptCaching":true,"fineTuning":false,"inputPrice":15,"outputPrice":60,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-o1-batch","slug":"openai-o1-batch","canonicalId":"openai-o1-batch","name":"o1 (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text","Image","File","Tools","Reasoning"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":0.0000075,"completion":0.00003},"inputPrice":7.5,"outputPrice":30,"cachedInputPrice":null,"price":"$7.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":0,"coding":39.7,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://openai.com/","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://openai.com/","sourceUpdatedAt":{},"updated":"2026-08-27","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":473,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-o1-batch","name":"o1 (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","File","Tools","Reasoning"],"contextWindow":"200000","maxOutputTokens":null,"apiAvailable":null,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":null,"reasoningCapability":true,"promptCaching":null,"fineTuning":false,"inputPrice":7.5,"outputPrice":30,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"cohere-command-r7b-12-2024","slug":"cohere-command-r7b-12-2024","canonicalId":"cohere-command-r7b-12-2024","name":"Command R7B (12-2024)","provider":"Cohere","family":null,"status":"active","variantType":"base","modelVersion":"cohere/command-r7b-12-2024","modalities":["Text"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"4000","apiAvailable":true,"pricing":{"prompt":3.75e-8,"completion":1.5e-7},"inputPrice":0.0375,"outputPrice":0.15,"cachedInputPrice":null,"price":"$0.04","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://cohere.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://cohere.com/"},"pricing":{"name":"Provider source","url":"https://cohere.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://cohere.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.cohere.com/docs/models","catalogSourceUrl":"https://cohere.com/","sourceUrl":"https://docs.cohere.com/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=cohere.com&sz=64","catalogRank":474,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"cohere-command-r7b-12-2024","name":"Command R7B (12-2024)","provider":"Cohere","family":null,"status":"active","variantType":"base","modelVersion":"cohere/command-r7b-12-2024","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text"],"contextWindow":"128000","maxOutputTokens":"4000","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.0375,"outputPrice":0.15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://cohere.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://cohere.com/"},"pricing":{"name":"Provider source","url":"https://cohere.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://cohere.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"meta-llama-llama-3-3-70b-instruct","slug":"meta-llama-llama-3-3-70b-instruct","canonicalId":"meta-llama-llama-3-3-70b-instruct","name":"Llama 3.3 70B Instruct","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta-llama/llama-3.3-70b-instruct","modalities":["Text","Tools"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"32768","apiAvailable":true,"pricing":{"prompt":5.9e-7,"completion":7.9e-7},"inputPrice":0.59,"outputPrice":0.7899999999999999,"cachedInputPrice":null,"price":"$0.59","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7.7,"coding":11.9,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}},"officialUrl":"https://www.llama.com/models/","catalogSourceUrl":"https://ai.meta.com/","sourceUrl":"https://www.llama.com/models/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=meta.com&sz=64","catalogRank":475,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"meta-llama-llama-3-3-70b-instruct","name":"Llama 3.3 70B Instruct","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta-llama/llama-3.3-70b-instruct","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools"],"contextWindow":"131072","maxOutputTokens":"32768","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.59,"outputPrice":0.7899999999999999,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"amazon-nova-lite-v1","slug":"amazon-nova-lite-v1","canonicalId":"amazon-nova-lite-v1","name":"Nova Lite 1.0","provider":"Amazon","family":null,"status":"active","variantType":"fast","modelVersion":"amazon/nova-lite-v1","modalities":["Text","Image","Tools"],"context_length":"300000","context":"300000","contextWindow":"300000","maxOutputTokens":"5120","apiAvailable":true,"pricing":{"prompt":6e-8,"completion":2.4e-7},"inputPrice":0.06,"outputPrice":0.24,"cachedInputPrice":null,"price":"$0.06","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":6.7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aws.amazon.com/"},"pricing":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aws.amazon.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","catalogSourceUrl":"https://aws.amazon.com/","sourceUrl":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=aws.amazon.com&sz=64","catalogRank":476,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"amazon-nova-lite-v1","name":"Nova Lite 1.0","provider":"Amazon","family":null,"status":"active","variantType":"fast","modelVersion":"amazon/nova-lite-v1","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","Tools"],"contextWindow":"300000","maxOutputTokens":"5120","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.06,"outputPrice":0.24,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aws.amazon.com/"},"pricing":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aws.amazon.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"amazon-nova-micro-v1","slug":"amazon-nova-micro-v1","canonicalId":"amazon-nova-micro-v1","name":"Nova Micro 1.0","provider":"Amazon","family":null,"status":"active","variantType":"base","modelVersion":"amazon/nova-micro-v1","modalities":["Text","Tools"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"5120","apiAvailable":true,"pricing":{"prompt":3.5e-8,"completion":1.4e-7},"inputPrice":0.035,"outputPrice":0.14,"cachedInputPrice":null,"price":"$0.04","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":5.9,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aws.amazon.com/"},"pricing":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aws.amazon.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","catalogSourceUrl":"https://aws.amazon.com/","sourceUrl":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=aws.amazon.com&sz=64","catalogRank":477,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"amazon-nova-micro-v1","name":"Nova Micro 1.0","provider":"Amazon","family":null,"status":"active","variantType":"base","modelVersion":"amazon/nova-micro-v1","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Tools"],"contextWindow":"128000","maxOutputTokens":"5120","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.035,"outputPrice":0.14,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aws.amazon.com/"},"pricing":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aws.amazon.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"amazon-nova-pro-v1","slug":"amazon-nova-pro-v1","canonicalId":"amazon-nova-pro-v1","name":"Nova Pro 1.0","provider":"Amazon","family":null,"status":"active","variantType":"base","modelVersion":"amazon/nova-pro-v1","modalities":["Text","Image","Tools"],"context_length":"300000","context":"300000","contextWindow":"300000","maxOutputTokens":"5120","apiAvailable":true,"pricing":{"prompt":8e-7,"completion":0.0000032},"inputPrice":0.7999999999999999,"outputPrice":3.1999999999999997,"cachedInputPrice":null,"price":"$0.80","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aws.amazon.com/"},"pricing":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aws.amazon.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","catalogSourceUrl":"https://aws.amazon.com/","sourceUrl":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=aws.amazon.com&sz=64","catalogRank":478,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"amazon-nova-pro-v1","name":"Nova Pro 1.0","provider":"Amazon","family":null,"status":"active","variantType":"base","modelVersion":"amazon/nova-pro-v1","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","Tools"],"contextWindow":"300000","maxOutputTokens":"5120","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.7999999999999999,"outputPrice":3.1999999999999997,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://aws.amazon.com/"},"pricing":{"name":"Provider source","url":"https://aws.amazon.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://aws.amazon.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-4o-2024-11-20","slug":"openai-gpt-4o-2024-11-20","canonicalId":"openai-gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","provider":"OpenAI","family":null,"status":"active","variantType":"dated","modelVersion":"openai/gpt-4o-2024-11-20","modalities":["Text","Image","File","Tools"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.00001},"inputPrice":2.5,"outputPrice":10,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":8.4,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-4o-2024-11-20","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-4o-2024-11-20","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":479,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","provider":"OpenAI","family":null,"status":"active","variantType":"dated","modelVersion":"openai/gpt-4o-2024-11-20","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools"],"contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":2.5,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-mistral-large-2407","slug":"mistralai-mistral-large-2407","canonicalId":"mistralai-mistral-large-2407","name":"Mistral Large 2407","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-large-2407","modalities":["Text","File","Tools"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"104857","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000006},"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":480,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-mistral-large-2407","name":"Mistral Large 2407","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-large-2407","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","File","Tools"],"contextWindow":"131072","maxOutputTokens":"104857","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen-2-5-coder-32b-instruct","slug":"qwen-qwen-2-5-coder-32b-instruct","canonicalId":"qwen-qwen-2-5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen-2.5-coder-32b-instruct","modalities":["Text"],"context_length":"32768","context":"32768","contextWindow":"32768","maxOutputTokens":"29491","apiAvailable":true,"pricing":{"prompt":6.6e-7,"completion":0.000001},"inputPrice":0.66,"outputPrice":1,"cachedInputPrice":null,"price":"$0.66","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":6.7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":481,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen-2-5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen-2.5-coder-32b-instruct","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"32768","maxOutputTokens":"29491","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.66,"outputPrice":1,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"thedrummer-unslopnemo-12b","slug":"thedrummer-unslopnemo-12b","canonicalId":"thedrummer-unslopnemo-12b","name":"UnslopNemo 12B","provider":"TheDrummer","family":null,"status":"active","variantType":"base","modelVersion":"thedrummer/unslopnemo-12b","modalities":["Text"],"context_length":"1024000","context":"1024000","contextWindow":"1024000","maxOutputTokens":"819200","apiAvailable":true,"pricing":{"prompt":4e-7,"completion":4e-7},"inputPrice":0.39999999999999997,"outputPrice":0.39999999999999997,"cachedInputPrice":null,"price":"$0.40","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":482,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"thedrummer-unslopnemo-12b","name":"UnslopNemo 12B","provider":"TheDrummer","family":null,"status":"active","variantType":"base","modelVersion":"thedrummer/unslopnemo-12b","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"1024000","maxOutputTokens":"819200","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.39999999999999997,"outputPrice":0.39999999999999997,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthracite-org-magnum-v4-72b","slug":"anthracite-org-magnum-v4-72b","canonicalId":"anthracite-org-magnum-v4-72b","name":"Magnum v4 72B","provider":"Anthraciteorg","family":null,"status":"active","variantType":"base","modelVersion":"anthracite-org/magnum-v4-72b","modalities":["Text"],"context_length":"32768","context":"32768","contextWindow":"32768","maxOutputTokens":"4096","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.000005},"inputPrice":2.5,"outputPrice":5,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":483,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthracite-org-magnum-v4-72b","name":"Magnum v4 72B","provider":"Anthraciteorg","family":null,"status":"active","variantType":"base","modelVersion":"anthracite-org/magnum-v4-72b","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"32768","maxOutputTokens":"4096","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":2.5,"outputPrice":5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-ministral-8b","slug":"mistralai-ministral-8b","canonicalId":"mistralai-ministral-8b","name":"Ministral 8B","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":1.1e-7,"completion":1.1e-7},"inputPrice":0.11,"outputPrice":0.11,"cachedInputPrice":null,"price":"$0.11","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://mistral.ai/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://mistral.ai/","sourceUpdatedAt":{},"updated":"2026-08-27","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":484,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-ministral-8b","name":"Ministral 8B","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text"],"contextWindow":"128000","maxOutputTokens":null,"apiAvailable":null,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"inputPrice":0.11,"outputPrice":0.11,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen-2-5-7b-instruct","slug":"qwen-qwen-2-5-7b-instruct","canonicalId":"qwen-qwen-2-5-7b-instruct","name":"Qwen2.5 7B Instruct","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen-2.5-7b-instruct","modalities":["Text","Tools"],"context_length":"32768","context":"32768","contextWindow":"32768","maxOutputTokens":"29491","apiAvailable":true,"pricing":{"prompt":1e-7,"completion":2e-7},"inputPrice":0.09999999999999999,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"price":"$0.10","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":485,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen-2-5-7b-instruct","name":"Qwen2.5 7B Instruct","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen-2.5-7b-instruct","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools"],"contextWindow":"32768","maxOutputTokens":"29491","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.09999999999999999,"outputPrice":0.19999999999999998,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"thedrummer-rocinante-12b","slug":"thedrummer-rocinante-12b","canonicalId":"thedrummer-rocinante-12b","name":"Rocinante 12B","provider":"TheDrummer","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":["Text"],"context_length":"65536","context":"65536","contextWindow":"65536","maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":2.5e-7,"completion":5e-7},"inputPrice":0.25,"outputPrice":0.5,"cachedInputPrice":null,"price":"$0.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":"/sources","catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-08-27","releaseDate":{},"knowledgeCutoff":null,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":"Open weights","providerIconUrl":null,"catalogRank":486,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"thedrummer-rocinante-12b","name":"Rocinante 12B","provider":"TheDrummer","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":{},"knowledgeCutoff":null,"license":"Open weights","modalities":["Text"],"contextWindow":"65536","maxOutputTokens":null,"apiAvailable":null,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"inputPrice":0.25,"outputPrice":0.5,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"meta-llama-llama-3-2-1b-instruct","slug":"meta-llama-llama-3-2-1b-instruct","canonicalId":"meta-llama-llama-3-2-1b-instruct","name":"Llama 3.2 1B Instruct","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta-llama/llama-3.2-1b-instruct","modalities":["Text"],"context_length":"60000","context":"60000","contextWindow":"60000","maxOutputTokens":"54000","apiAvailable":true,"pricing":{"prompt":2.7e-8,"completion":2.01e-7},"inputPrice":0.027,"outputPrice":0.201,"cachedInputPrice":null,"price":"$0.03","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":4.8,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}},"officialUrl":"https://www.llama.com/models/","catalogSourceUrl":"https://ai.meta.com/","sourceUrl":"https://www.llama.com/models/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=meta.com&sz=64","catalogRank":487,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"meta-llama-llama-3-2-1b-instruct","name":"Llama 3.2 1B Instruct","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta-llama/llama-3.2-1b-instruct","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"60000","maxOutputTokens":"54000","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.027,"outputPrice":0.201,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"meta-llama-llama-3-2-3b-instruct","slug":"meta-llama-llama-3-2-3b-instruct","canonicalId":"meta-llama-llama-3-2-3b-instruct","name":"Llama 3.2 3B Instruct","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta-llama/llama-3.2-3b-instruct","modalities":["Text"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"pricing":{"prompt":5e-8,"completion":3.3e-7},"inputPrice":0.049999999999999996,"outputPrice":0.33,"cachedInputPrice":null,"price":"$0.05","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":5.7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}},"officialUrl":"https://www.llama.com/models/","catalogSourceUrl":"https://ai.meta.com/","sourceUrl":"https://www.llama.com/models/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=meta.com&sz=64","catalogRank":488,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"meta-llama-llama-3-2-3b-instruct","name":"Llama 3.2 3B Instruct","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta-llama/llama-3.2-3b-instruct","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.049999999999999996,"outputPrice":0.33,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"qwen-qwen-2-5-72b-instruct","slug":"qwen-qwen-2-5-72b-instruct","canonicalId":"qwen-qwen-2-5-72b-instruct","name":"Qwen2.5 72B Instruct","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen-2.5-72b-instruct","modalities":["Text","Tools"],"context_length":"32768","context":"32768","contextWindow":"32768","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":3.6e-7,"completion":4e-7},"inputPrice":0.36,"outputPrice":0.39999999999999997,"cachedInputPrice":null,"price":"$0.36","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7.7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://qwenlm.github.io/","catalogSourceUrl":"https://qwen.ai/","sourceUrl":"https://qwenlm.github.io/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=qwen.ai&sz=64","catalogRank":489,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"qwen-qwen-2-5-72b-instruct","name":"Qwen2.5 72B Instruct","provider":"Qwen","family":null,"status":"active","variantType":"base","modelVersion":"qwen/qwen-2.5-72b-instruct","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools"],"contextWindow":"32768","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.36,"outputPrice":0.39999999999999997,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://qwen.ai/"},"pricing":{"name":"Provider source","url":"https://qwen.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://qwen.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"cohere-command-r-08-2024","slug":"cohere-command-r-08-2024","canonicalId":"cohere-command-r-08-2024","name":"Command R+ (08-2024)","provider":"Cohere","family":null,"status":"active","variantType":"base","modelVersion":"cohere/command-r-plus-08-2024","modalities":["Text","Tools"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"4000","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.00001},"inputPrice":2.5,"outputPrice":10,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://cohere.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://cohere.com/"},"pricing":{"name":"Provider source","url":"https://cohere.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://cohere.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.cohere.com/docs/models","catalogSourceUrl":"https://cohere.com/","sourceUrl":"https://docs.cohere.com/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=cohere.com&sz=64","catalogRank":490,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"cohere-command-r-08-2024","name":"Command R+ (08-2024)","provider":"Cohere","family":null,"status":"active","variantType":"base","modelVersion":"cohere/command-r-plus-08-2024","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Tools"],"contextWindow":"128000","maxOutputTokens":"4000","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":2.5,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://cohere.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://cohere.com/"},"pricing":{"name":"Provider source","url":"https://cohere.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://cohere.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"sao10k-l3-1-euryale-70b","slug":"sao10k-l3-1-euryale-70b","canonicalId":"sao10k-l3-1-euryale-70b","name":"Llama 3.1 Euryale 70B v2.2","provider":"Sao10K","family":null,"status":"active","variantType":"base","modelVersion":"sao10k/l3.1-euryale-70b","modalities":["Text"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":8.5e-7,"completion":8.5e-7},"inputPrice":0.85,"outputPrice":0.85,"cachedInputPrice":null,"price":"$0.85","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":491,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"sao10k-l3-1-euryale-70b","name":"Llama 3.1 Euryale 70B v2.2","provider":"Sao10K","family":null,"status":"active","variantType":"base","modelVersion":"sao10k/l3.1-euryale-70b","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.85,"outputPrice":0.85,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"nousresearch-hermes-3-llama-3-1-70b","slug":"nousresearch-hermes-3-llama-3-1-70b","canonicalId":"nousresearch-hermes-3-llama-3-1-70b","name":"Hermes 3 70B Instruct","provider":"Nous","family":null,"status":"active","variantType":"base","modelVersion":"nousresearch/hermes-3-llama-3.1-70b","modalities":["Text"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":7e-7,"completion":7e-7},"inputPrice":0.7,"outputPrice":0.7,"cachedInputPrice":null,"price":"$0.70","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":6.7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":492,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"nousresearch-hermes-3-llama-3-1-70b","name":"Hermes 3 70B Instruct","provider":"Nous","family":null,"status":"active","variantType":"base","modelVersion":"nousresearch/hermes-3-llama-3.1-70b","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.7,"outputPrice":0.7,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"nousresearch-hermes-3-llama-3-1-405b","slug":"nousresearch-hermes-3-llama-3-1-405b","canonicalId":"nousresearch-hermes-3-llama-3-1-405b","name":"Hermes 3 405B Instruct","provider":"Nous","family":null,"status":"active","variantType":"base","modelVersion":"nousresearch/hermes-3-llama-3.1-405b","modalities":["Text"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000001},"inputPrice":1,"outputPrice":1,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7.4,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":493,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"nousresearch-hermes-3-llama-3-1-405b","name":"Hermes 3 405B Instruct","provider":"Nous","family":null,"status":"active","variantType":"base","modelVersion":"nousresearch/hermes-3-llama-3.1-405b","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":1,"outputPrice":1,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"sao10k-l3-lunaris-8b","slug":"sao10k-l3-lunaris-8b","canonicalId":"sao10k-l3-lunaris-8b","name":"Llama 3 8B Lunaris","provider":"Sao10K","family":null,"status":"active","variantType":"base","modelVersion":"sao10k/l3-lunaris-8b","modalities":["Text"],"context_length":"8192","context":"8192","contextWindow":"8192","maxOutputTokens":"7372","apiAvailable":true,"pricing":{"prompt":4e-8,"completion":5e-8},"inputPrice":0.04,"outputPrice":0.049999999999999996,"cachedInputPrice":null,"price":"$0.04","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":494,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"sao10k-l3-lunaris-8b","name":"Llama 3 8B Lunaris","provider":"Sao10K","family":null,"status":"active","variantType":"base","modelVersion":"sao10k/l3-lunaris-8b","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"8192","maxOutputTokens":"7372","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.04,"outputPrice":0.049999999999999996,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-4o-2024-08-06","slug":"openai-gpt-4o-2024-08-06","canonicalId":"openai-gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","provider":"OpenAI","family":null,"status":"active","variantType":"dated","modelVersion":"openai/gpt-4o-2024-08-06","modalities":["Text","Image","File","Tools"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.00001},"inputPrice":2.5,"outputPrice":10,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7.7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-4o-2024-08-06","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-4o-2024-08-06","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":495,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","provider":"OpenAI","family":null,"status":"active","variantType":"dated","modelVersion":"openai/gpt-4o-2024-08-06","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools"],"contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":2.5,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"meta-llama-llama-3-1-70b-instruct","slug":"meta-llama-llama-3-1-70b-instruct","canonicalId":"meta-llama-llama-3-1-70b-instruct","name":"Llama 3.1 70B Instruct","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta-llama/llama-3.1-70b-instruct","modalities":["Text","Tools"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":4e-7,"completion":4e-7},"inputPrice":0.39999999999999997,"outputPrice":0.39999999999999997,"cachedInputPrice":null,"price":"$0.40","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":6.6,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}},"officialUrl":"https://www.llama.com/models/","catalogSourceUrl":"https://ai.meta.com/","sourceUrl":"https://www.llama.com/models/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=meta.com&sz=64","catalogRank":496,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"meta-llama-llama-3-1-70b-instruct","name":"Llama 3.1 70B Instruct","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta-llama/llama-3.1-70b-instruct","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools"],"contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.39999999999999997,"outputPrice":0.39999999999999997,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"meta-llama-llama-3-1-8b-instruct","slug":"meta-llama-llama-3-1-8b-instruct","canonicalId":"meta-llama-llama-3-1-8b-instruct","name":"Llama 3.1 8B Instruct","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta-llama/llama-3.1-8b-instruct","modalities":["Text","Tools"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"pricing":{"prompt":5e-8,"completion":8e-8},"inputPrice":0.049999999999999996,"outputPrice":0.08,"cachedInputPrice":null,"price":"$0.05","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":6.9,"coding":5.4,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}},"officialUrl":"https://www.llama.com/models/","catalogSourceUrl":"https://ai.meta.com/","sourceUrl":"https://www.llama.com/models/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=meta.com&sz=64","catalogRank":497,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"meta-llama-llama-3-1-8b-instruct","name":"Llama 3.1 8B Instruct","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":"meta-llama/llama-3.1-8b-instruct","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools"],"contextWindow":"131072","maxOutputTokens":"117964","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.049999999999999996,"outputPrice":0.08,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.meta.com/"},"pricing":{"name":"Provider source","url":"https://ai.meta.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.meta.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-mistral-nemo","slug":"mistralai-mistral-nemo","canonicalId":"mistralai-mistral-nemo","name":"Mistral Nemo","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-nemo","modalities":["Text","Tools"],"context_length":"131072","context":"131072","contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":2.9e-8,"completion":3e-8},"inputPrice":0.029,"outputPrice":0.03,"cachedInputPrice":null,"price":"$0.03","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":498,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-mistral-nemo","name":"Mistral Nemo","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-nemo","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","Tools"],"contextWindow":"131072","maxOutputTokens":"16384","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.029,"outputPrice":0.03,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-4o-mini","slug":"openai-gpt-4o-mini","canonicalId":"openai-gpt-4o-mini","name":"GPT-4o-mini","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/gpt-4o-mini","modalities":["Text","Image","File","Tools"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":1.5e-7,"completion":6e-7},"inputPrice":0.15,"outputPrice":0.6,"cachedInputPrice":null,"price":"$0.15","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":6.7,"coding":11.4,"agents":0,"speed":null,"latency":350,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-4o-mini","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-4o-mini","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":499,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-4o-mini","name":"GPT-4o-mini","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/gpt-4o-mini","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools"],"contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.15,"outputPrice":0.6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-4o-mini-2024-07-18","slug":"openai-gpt-4o-mini-2024-07-18","canonicalId":"openai-gpt-4o-mini-2024-07-18","name":"GPT-4o-mini (2024-07-18)","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/gpt-4o-mini-2024-07-18","modalities":["Text","Image","File","Tools"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":1.5e-7,"completion":6e-7},"inputPrice":0.15,"outputPrice":0.6,"cachedInputPrice":null,"price":"$0.15","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-4o-mini-2024-07-18","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-4o-mini-2024-07-18","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":500,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-4o-mini-2024-07-18","name":"GPT-4o-mini (2024-07-18)","provider":"OpenAI","family":null,"status":"active","variantType":"fast","modelVersion":"openai/gpt-4o-mini-2024-07-18","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools"],"contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.15,"outputPrice":0.6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-4o-mini-batch","slug":"openai-gpt-4o-mini-batch","canonicalId":"openai-gpt-4o-mini-batch","name":"GPT-4o-mini (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-4o-mini","modalities":["Text","Image","File","Tools"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":7.5e-8,"completion":3e-7},"inputPrice":0.075,"outputPrice":0.3,"cachedInputPrice":null,"price":"$0.07","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":6.7,"coding":11.4,"agents":0,"speed":null,"latency":350,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-4o-mini:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-4o-mini:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":501,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-4o-mini-batch","name":"GPT-4o-mini (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-4o-mini","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools"],"contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.075,"outputPrice":0.3,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"google-gemma-2-27b-it","slug":"google-gemma-2-27b-it","canonicalId":"google-gemma-2-27b-it","name":"Gemma 2 27B","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemma-2-27b-it","modalities":["Text"],"context_length":"8192","context":"8192","contextWindow":"8192","maxOutputTokens":"2048","apiAvailable":true,"pricing":{"prompt":6.5e-7,"completion":6.5e-7},"inputPrice":0.65,"outputPrice":0.65,"cachedInputPrice":null,"price":"$0.65","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}},"officialUrl":"https://ai.google.dev/gemini-api/docs/models","catalogSourceUrl":"https://ai.google.dev/","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=google.com&sz=64","catalogRank":502,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"google-gemma-2-27b-it","name":"Gemma 2 27B","provider":"Google","family":null,"status":"active","variantType":"base","modelVersion":"google/gemma-2-27b-it","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"8192","maxOutputTokens":"2048","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.65,"outputPrice":0.65,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://ai.google.dev/"},"pricing":{"name":"Provider source","url":"https://ai.google.dev/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://ai.google.dev/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-4o","slug":"openai-gpt-4o","canonicalId":"openai-gpt-4o","name":"GPT-4o","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-4o","modalities":["Text","Image","File","Tools"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":0.0000025,"completion":0.00001},"inputPrice":2.5,"outputPrice":10,"cachedInputPrice":null,"price":"$2.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-4o","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-4o","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":503,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-4o","name":"GPT-4o","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-4o","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools"],"contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":2.5,"outputPrice":10,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-4o-2024-05-13","slug":"openai-gpt-4o-2024-05-13","canonicalId":"openai-gpt-4o-2024-05-13","name":"GPT-4o (2024-05-13)","provider":"OpenAI","family":null,"status":"active","variantType":"dated","modelVersion":"openai/gpt-4o-2024-05-13","modalities":["Text","Image","File","Tools"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"4096","apiAvailable":true,"pricing":{"prompt":0.000005,"completion":0.000015},"inputPrice":5,"outputPrice":15,"cachedInputPrice":null,"price":"$5.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7.3,"coding":24.2,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-4o-2024-05-13","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-4o-2024-05-13","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":504,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-4o-2024-05-13","name":"GPT-4o (2024-05-13)","provider":"OpenAI","family":null,"status":"active","variantType":"dated","modelVersion":"openai/gpt-4o-2024-05-13","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools"],"contextWindow":"128000","maxOutputTokens":"4096","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":5,"outputPrice":15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-4o-batch","slug":"openai-gpt-4o-batch","canonicalId":"openai-gpt-4o-batch","name":"GPT-4o (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-4o","modalities":["Text","Image","File","Tools"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"pricing":{"prompt":0.00000125,"completion":0.000005},"inputPrice":1.25,"outputPrice":5,"cachedInputPrice":null,"price":"$1.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-4o:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-4o:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":505,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-4o-batch","name":"GPT-4o (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-4o","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","File","Tools"],"contextWindow":"128000","maxOutputTokens":"16384","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":1.25,"outputPrice":5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-mixtral-8x22b-instruct","slug":"mistralai-mixtral-8x22b-instruct","canonicalId":"mistralai-mixtral-8x22b-instruct","name":"Mixtral 8x22B Instruct","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mixtral-8x22b-instruct","modalities":["Text","File","Tools"],"context_length":"65536","context":"65536","contextWindow":"65536","maxOutputTokens":"52428","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000006},"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":5.7,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":506,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-mixtral-8x22b-instruct","name":"Mixtral 8x22B Instruct","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mixtral-8x22b-instruct","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text","File","Tools"],"contextWindow":"65536","maxOutputTokens":"52428","apiAvailable":true,"openWeights":true,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"microsoft-wizardlm-2-8x22b","slug":"microsoft-wizardlm-2-8x22b","canonicalId":"microsoft-wizardlm-2-8x22b","name":"WizardLM-2 8x22B","provider":"Microsoft","family":null,"status":"active","variantType":"base","modelVersion":"microsoft/wizardlm-2-8x22b","modalities":["Text"],"context_length":"65535","context":"65535","contextWindow":"65535","maxOutputTokens":"8000","apiAvailable":true,"pricing":{"prompt":6.2e-7,"completion":6.2e-7},"inputPrice":0.62,"outputPrice":0.62,"cachedInputPrice":null,"price":"$0.62","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://microsoft.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://microsoft.com/"},"pricing":{"name":"Provider source","url":"https://microsoft.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://microsoft.com/"},"metrics":{},"fields":{}},"officialUrl":"https://azure.microsoft.com/en-us/products/ai-services/ai-model-catalog","catalogSourceUrl":"https://microsoft.com/","sourceUrl":"https://azure.microsoft.com/en-us/products/ai-services/ai-model-catalog","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":"https://www.google.com/s2/favicons?domain=microsoft.com&sz=64","catalogRank":507,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"microsoft-wizardlm-2-8x22b","name":"WizardLM-2 8x22B","provider":"Microsoft","family":null,"status":"active","variantType":"base","modelVersion":"microsoft/wizardlm-2-8x22b","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"65535","maxOutputTokens":"8000","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.62,"outputPrice":0.62,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://microsoft.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://microsoft.com/"},"pricing":{"name":"Provider source","url":"https://microsoft.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://microsoft.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-4-turbo","slug":"openai-gpt-4-turbo","canonicalId":"openai-gpt-4-turbo","name":"GPT-4 Turbo","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-4-turbo","modalities":["Text","Image","Tools"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"4096","apiAvailable":true,"pricing":{"prompt":0.00001,"completion":0.00003},"inputPrice":10,"outputPrice":30,"cachedInputPrice":null,"price":"$10.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7,"coding":21.5,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-4-turbo","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-4-turbo","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":508,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-4-turbo","name":"GPT-4 Turbo","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-4-turbo","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","Tools"],"contextWindow":"128000","maxOutputTokens":"4096","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":10,"outputPrice":30,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-4-turbo-batch","slug":"openai-gpt-4-turbo-batch","canonicalId":"openai-gpt-4-turbo-batch","name":"GPT-4 Turbo (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-4-turbo","modalities":["Text","Image","Tools"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"4096","apiAvailable":true,"pricing":{"prompt":0.000005,"completion":0.000015},"inputPrice":5,"outputPrice":15,"cachedInputPrice":null,"price":"$5.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":7,"coding":21.5,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-4-turbo:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-4-turbo:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":509,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-4-turbo-batch","name":"GPT-4 Turbo (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-4-turbo","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","Tools"],"contextWindow":"128000","maxOutputTokens":"4096","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":5,"outputPrice":15,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"anthropic-claude-3-haiku","slug":"anthropic-claude-3-haiku","canonicalId":"anthropic-claude-3-haiku","name":"Claude 3 Haiku","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-3-haiku","modalities":["Text","Image","Tools"],"context_length":"200000","context":"200000","contextWindow":"200000","maxOutputTokens":"4096","apiAvailable":true,"pricing":{"prompt":2.5e-7,"completion":0.00000125},"inputPrice":0.25,"outputPrice":1.25,"cachedInputPrice":null,"price":"$0.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.anthropic.com/en/docs/about-claude/models","catalogSourceUrl":"https://anthropic.com/","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","sourceUpdatedAt":{},"updated":"2026-09-26","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=anthropic.com&sz=64","catalogRank":510,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"anthropic-claude-3-haiku","name":"Claude 3 Haiku","provider":"Anthropic","family":null,"status":"active","variantType":"base","modelVersion":"anthropic/claude-3-haiku","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Image","Tools"],"contextWindow":"200000","maxOutputTokens":"4096","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":0.25,"outputPrice":1.25,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://anthropic.com/"},"pricing":{"name":"Provider source","url":"https://anthropic.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://anthropic.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mistralai-mistral-large","slug":"mistralai-mistral-large","canonicalId":"mistralai-mistral-large","name":"Mistral Large","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-large","modalities":["Text","File","Tools"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"102400","apiAvailable":true,"pricing":{"prompt":0.000002,"completion":0.000006},"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"price":"$2.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":5.8,"coding":0,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}},"officialUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","catalogSourceUrl":"https://mistral.ai/","sourceUrl":"https://docs.mistral.ai/getting-started/models/models_overview/","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=mistral.ai&sz=64","catalogRank":511,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mistralai-mistral-large","name":"Mistral Large","provider":"Mistral","family":null,"status":"active","variantType":"base","modelVersion":"mistralai/mistral-large","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","File","Tools"],"contextWindow":"128000","maxOutputTokens":"102400","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":true,"fineTuning":false,"inputPrice":2,"outputPrice":6,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://mistral.ai/"},"pricing":{"name":"Provider source","url":"https://mistral.ai/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://mistral.ai/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-3-5-turbo-0613","slug":"openai-gpt-3-5-turbo-0613","canonicalId":"openai-gpt-3-5-turbo-0613","name":"GPT-3.5 Turbo (older v0613)","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-3.5-turbo-0613","modalities":["Text","Tools"],"context_length":"4095","context":"4095","contextWindow":"4095","maxOutputTokens":"3685","apiAvailable":true,"pricing":{"prompt":0.000001,"completion":0.000002},"inputPrice":1,"outputPrice":2,"cachedInputPrice":null,"price":"$1.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-3.5-turbo-0613","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-3.5-turbo-0613","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":512,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-3-5-turbo-0613","name":"GPT-3.5 Turbo (older v0613)","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-3.5-turbo-0613","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Tools"],"contextWindow":"4095","maxOutputTokens":"3685","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":1,"outputPrice":2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-4-turbo-preview","slug":"openai-gpt-4-turbo-preview","canonicalId":"openai-gpt-4-turbo-preview","name":"GPT-4 Turbo Preview","provider":"OpenAI","family":null,"status":"active","variantType":"preview","modelVersion":"openai/gpt-4-turbo-preview","modalities":["Text","Tools"],"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":"4096","apiAvailable":true,"pricing":{"prompt":0.00001,"completion":0.00003},"inputPrice":10,"outputPrice":30,"cachedInputPrice":null,"price":"$10.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-4-turbo-preview","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-4-turbo-preview","sourceUpdatedAt":{},"updated":"2026-09-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":513,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-4-turbo-preview","name":"GPT-4 Turbo Preview","provider":"OpenAI","family":null,"status":"active","variantType":"preview","modelVersion":"openai/gpt-4-turbo-preview","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Tools"],"contextWindow":"128000","maxOutputTokens":"4096","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":10,"outputPrice":30,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openrouter-auto","slug":"openrouter-auto","canonicalId":"openrouter-auto","name":"Auto Router","provider":"OpenRouter","family":null,"status":"active","variantType":"router","modelVersion":"openrouter/auto","modalities":["Text","Image","Audio","File","Video","Tools"],"context_length":"2000000","context":"2000000","contextWindow":"2000000","maxOutputTokens":null,"apiAvailable":true,"pricing":{"prompt":null,"completion":null},"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"price":"N/A","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":null,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":null,"catalogRank":514,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openrouter-auto","name":"Auto Router","provider":"OpenRouter","family":null,"status":"active","variantType":"router","modelVersion":"openrouter/auto","releaseDate":{},"knowledgeCutoff":null,"license":"Proprietary","modalities":["Text","Image","Audio","File","Video","Tools"],"contextWindow":"2000000","maxOutputTokens":null,"apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":true,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-3-5-turbo-instruct","slug":"openai-gpt-3-5-turbo-instruct","canonicalId":"openai-gpt-3-5-turbo-instruct","name":"GPT-3.5 Turbo Instruct","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-3.5-turbo-instruct","modalities":["Text"],"context_length":"4095","context":"4095","contextWindow":"4095","maxOutputTokens":"3685","apiAvailable":true,"pricing":{"prompt":0.0000015,"completion":0.000002},"inputPrice":1.5,"outputPrice":2,"cachedInputPrice":null,"price":"$1.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-3.5-turbo-instruct","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-3.5-turbo-instruct","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":515,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-3-5-turbo-instruct","name":"GPT-3.5 Turbo Instruct","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-3.5-turbo-instruct","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text"],"contextWindow":"4095","maxOutputTokens":"3685","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":1.5,"outputPrice":2,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-3-5-turbo-16k","slug":"openai-gpt-3-5-turbo-16k","canonicalId":"openai-gpt-3-5-turbo-16k","name":"GPT-3.5 Turbo 16k","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-3.5-turbo-16k","modalities":["Text","Tools"],"context_length":"16385","context":"16385","contextWindow":"16385","maxOutputTokens":"4096","apiAvailable":true,"pricing":{"prompt":0.000003,"completion":0.000004},"inputPrice":3,"outputPrice":4,"cachedInputPrice":null,"price":"$3.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-3.5-turbo-16k","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-3.5-turbo-16k","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":516,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-3-5-turbo-16k","name":"GPT-3.5 Turbo 16k","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-3.5-turbo-16k","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Tools"],"contextWindow":"16385","maxOutputTokens":"4096","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":3,"outputPrice":4,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"mancer-weaver","slug":"mancer-weaver","canonicalId":"mancer-weaver","name":"Weaver (alpha)","provider":"Mancer","family":null,"status":"active","variantType":"base","modelVersion":"mancer/weaver","modalities":["Text"],"context_length":"8000","context":"8000","contextWindow":"8000","maxOutputTokens":"6000","apiAvailable":true,"pricing":{"prompt":4e-7,"completion":7.5e-7},"inputPrice":0.39999999999999997,"outputPrice":0.75,"cachedInputPrice":null,"price":"$0.40","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":null,"catalogRank":517,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"mancer-weaver","name":"Weaver (alpha)","provider":"Mancer","family":null,"status":"active","variantType":"base","modelVersion":"mancer/weaver","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text"],"contextWindow":"8000","maxOutputTokens":"6000","apiAvailable":true,"openWeights":false,"toolCalling":false,"structuredOutput":false,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.39999999999999997,"outputPrice":0.75,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"undi95-remm-slerp-l2-13b","slug":"undi95-remm-slerp-l2-13b","canonicalId":"undi95-remm-slerp-l2-13b","name":"ReMM SLERP 13B","provider":"Undi95","family":null,"status":"active","variantType":"base","modelVersion":"undi95/remm-slerp-l2-13b","modalities":["Text"],"context_length":"6144","context":"6144","contextWindow":"6144","maxOutputTokens":"5529","apiAvailable":true,"pricing":{"prompt":3.5e-7,"completion":6.5e-7},"inputPrice":0.35,"outputPrice":0.65,"cachedInputPrice":null,"price":"$0.35","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":518,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"undi95-remm-slerp-l2-13b","name":"ReMM SLERP 13B","provider":"Undi95","family":null,"status":"active","variantType":"base","modelVersion":"undi95/remm-slerp-l2-13b","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"6144","maxOutputTokens":"5529","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.35,"outputPrice":0.65,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"gryphe-mythomax-l2-13b","slug":"gryphe-mythomax-l2-13b","canonicalId":"gryphe-mythomax-l2-13b","name":"MythoMax 13B","provider":"Gryphe","family":null,"status":"active","variantType":"base","modelVersion":"gryphe/mythomax-l2-13b","modalities":["Text"],"context_length":"8192","context":"8192","contextWindow":"8192","maxOutputTokens":"3686","apiAvailable":true,"pricing":{"prompt":8e-8,"completion":1.1e-7},"inputPrice":0.08,"outputPrice":0.11,"cachedInputPrice":null,"price":"$0.08","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":"/sources","sourceUrl":"/sources","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Open weights","providerIconUrl":null,"catalogRank":519,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"gryphe-mythomax-l2-13b","name":"MythoMax 13B","provider":"Gryphe","family":null,"status":"active","variantType":"base","modelVersion":"gryphe/mythomax-l2-13b","releaseDate":{},"knowledgeCutoff":{},"license":"Open weights","modalities":["Text"],"contextWindow":"8192","maxOutputTokens":"3686","apiAvailable":true,"openWeights":true,"toolCalling":false,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.08,"outputPrice":0.11,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"/sources"},"pricing":{"name":"Provider source","url":"/sources","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"/sources"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-3-5-turbo","slug":"openai-gpt-3-5-turbo","canonicalId":"openai-gpt-3-5-turbo","name":"GPT-3.5 Turbo","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-3.5-turbo","modalities":["Text","Tools"],"context_length":"16385","context":"16385","contextWindow":"16385","maxOutputTokens":"4096","apiAvailable":true,"pricing":{"prompt":5e-7,"completion":0.0000015},"inputPrice":0.5,"outputPrice":1.5,"cachedInputPrice":null,"price":"$0.50","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":5.5,"coding":10.7,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-3.5-turbo","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-3.5-turbo","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":520,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-3-5-turbo","name":"GPT-3.5 Turbo","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-3.5-turbo","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Tools"],"contextWindow":"16385","maxOutputTokens":"4096","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.5,"outputPrice":1.5,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-3-5-turbo-batch","slug":"openai-gpt-3-5-turbo-batch","canonicalId":"openai-gpt-3-5-turbo-batch","name":"GPT-3.5 Turbo (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-3.5-turbo","modalities":["Text","Tools"],"context_length":"16385","context":"16385","contextWindow":"16385","maxOutputTokens":"4096","apiAvailable":true,"pricing":{"prompt":2.5e-7,"completion":7.5e-7},"inputPrice":0.25,"outputPrice":0.75,"cachedInputPrice":null,"price":"$0.25","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":5.5,"coding":10.7,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-3.5-turbo:batch","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-3.5-turbo:batch","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":521,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-3-5-turbo-batch","name":"GPT-3.5 Turbo (batch)","provider":"OpenAI","family":null,"status":"active","variantType":"batch","modelVersion":"openai/gpt-3.5-turbo","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Tools"],"contextWindow":"16385","maxOutputTokens":"4096","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":0.25,"outputPrice":0.75,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"openai-gpt-4","slug":"openai-gpt-4","canonicalId":"openai-gpt-4","name":"GPT-4","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-4","modalities":["Text","Tools"],"context_length":"8191","context":"8191","contextWindow":"8191","maxOutputTokens":"4096","apiAvailable":true,"pricing":{"prompt":0.00003,"completion":0.00006},"inputPrice":30,"outputPrice":60,"cachedInputPrice":null,"price":"$30.00","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":6.7,"coding":13.1,"agents":0,"speed":null,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Database record","sourceName":"Database record","sourceFetchedAt":{},"sourceSnapshotStatus":"success","provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}},"officialUrl":"https://developers.openai.com/api/docs/models/gpt-4","catalogSourceUrl":"https://openai.com/","sourceUrl":"https://developers.openai.com/api/docs/models/gpt-4","sourceUpdatedAt":{},"updated":"2026-10-14","releaseDate":{},"knowledgeCutoff":{},"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"lastVerifiedAt":{},"license":"Proprietary","providerIconUrl":"https://www.google.com/s2/favicons?domain=openai.com&sz=64","catalogRank":522,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"openai-gpt-4","name":"GPT-4","provider":"OpenAI","family":null,"status":"active","variantType":"base","modelVersion":"openai/gpt-4","releaseDate":{},"knowledgeCutoff":{},"license":"Proprietary","modalities":["Text","Tools"],"contextWindow":"8191","maxOutputTokens":"4096","apiAvailable":true,"openWeights":false,"toolCalling":true,"structuredOutput":true,"webSearch":false,"reasoningCapability":false,"promptCaching":false,"fineTuning":false,"inputPrice":30,"outputPrice":60,"cachedInputPrice":null,"lastVerifiedAt":{}},"provenance":{"catalog":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","fetchedAt":{},"sourceUrl":"https://openai.com/"},"pricing":{"name":"Provider source","url":"https://openai.com/","evidenceClass":"catalog fact","observedAt":{},"sourceUrl":"https://openai.com/"},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}},{"id":"llama-3-1-405b","slug":"llama-3-1-405b","canonicalId":"llama-3-1-405b","name":"Llama 3.1 405B","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":null,"modalities":null,"context_length":"128000","context":"128000","contextWindow":"128000","maxOutputTokens":null,"apiAvailable":null,"pricing":{"prompt":null,"completion":null},"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"price":"N/A","overall":null,"fit":null,"overallScore":null,"overallScoreVersion":null,"overallScoreCoverage":0,"overallScoreInputs":[],"overallScoreMissing":["overall","coding","reasoning","agents","computer_use","browsing","terminal"],"reasoning":null,"coding":null,"agents":null,"speed":969,"latency":null,"benchmarkScores":{},"benchmarkProvenance":{},"benchmarkSource":"/methodology","benchmarkUpdated":null,"source":"Imported catalog record","sourceName":"Imported catalog record","sourceFetchedAt":null,"sourceSnapshotStatus":"not_synced","provenance":{"catalog":{"name":"Imported catalog record","url":null,"evidenceClass":"catalog fact","fetchedAt":null,"sourceUrl":null},"pricing":{"name":"Not reported","url":null,"evidenceClass":"catalog fact","observedAt":null,"sourceUrl":null},"metrics":{},"fields":{}},"officialUrl":null,"catalogSourceUrl":null,"sourceUrl":null,"sourceUpdatedAt":null,"updated":null,"releaseDate":null,"knowledgeCutoff":null,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"lastVerifiedAt":null,"license":"Llama 3.1 Community License","providerIconUrl":"https://www.google.com/s2/favicons?domain=meta.com&sz=64","catalogRank":523,"evidenceLayers":{"publishedFacts":{"fields":{"canonicalId":"llama-3-1-405b","name":"Llama 3.1 405B","provider":"Meta","family":null,"status":"active","variantType":"base","modelVersion":null,"releaseDate":null,"knowledgeCutoff":null,"license":"Llama 3.1 Community License","modalities":null,"contextWindow":"128000","maxOutputTokens":null,"apiAvailable":null,"openWeights":true,"toolCalling":false,"structuredOutput":false,"webSearch":null,"reasoningCapability":false,"promptCaching":null,"fineTuning":false,"inputPrice":null,"outputPrice":null,"cachedInputPrice":null,"lastVerifiedAt":null},"provenance":{"catalog":{"name":"Imported catalog record","url":null,"evidenceClass":"catalog fact","fetchedAt":null,"sourceUrl":null},"pricing":{"name":"Not reported","url":null,"evidenceClass":"catalog fact","observedAt":null,"sourceUrl":null},"metrics":{},"fields":{}}},"publishedBenchmarks":{"scores":{},"provenance":{},"composite":null},"topllmEvaluation":{"status":"not_available","scores":{"taskFit":null,"costEfficiency":null,"agent":null,"ui":null},"methodologyUrl":"/methodology","evidenceClass":"TOPLLM_EVALUATION","note":"TopLLM first-party task evaluations will be published separately from external benchmark results."}}}]