What it is
Published Best Overall (Humanity's Last Exam) scores.
← Back to leaderboards
BENCHMARK RECORD
Humanity's Last Exam
Source-linked result details from the TopLLM database.
BENCHMARK RECORD · 2026-08-25
Humanity's Last Exam
What it tests
Published Best Overall (Humanity's Last Exam) scores.
How to read it
Scores are benchmark-specific and missing values are not estimated.
24 published entries64.7 top reported scoreoverall evaluation domain
Published leaders
Each bar is scaled only within this benchmark.
01Claude Opus 564.702Claude Mythos 564.503Claude Opus 4.857.904Claude Sonnet 557.405Kimi K356.006Z.ai: GLM 5.3 Flash55.307GLM 5.254.708Kimi K2.654.009DeepSeek V4 Flash51.610DeepSeek V4 Pro48.211GPT-5.6 Sol47.212Gemini 3 Pro45.813Kimi K2 Thinking44.914Gemini 3.1 Pro44.415GPT-5.5 Pro43.116GPT-5.541.417Gemini 3.5 Flash40.218Claude Opus 4.640.019GPT-535.220Kimi K2.530.121Grok 425.422GPT oss 120b14.923GPT oss 20b10.924DeepSeek-R18.6
Scores are benchmark-specific. Missing values remain N/A and are never inferred from another evaluation.
Compare in the benchmark matrix →