MODEL DETAIL · Anthropic
Anthropic: Claude Opus 4.8
Source-linked record by Anthropic
Anthropic: Claude Opus 4.8 supports text, image, file, tools, reasoning workflows. Published fields are kept separate from benchmark evidence and community signals.
Fit score61.1Contextual · fit-v1
Coding88.6Database signal
Reasoning57.3Database signal
Context window1000000Published limit
Input price$5.00Per 1M tokens
Released2026-05-27Source date
DATABASE MODEL RECORD
What this record says.
Anthropic: Claude Opus 4.8 is cataloged by Anthropic with source-linked capabilities, pricing, release metadata, and explicitly separated evaluation evidence.
Freshness not availableConfidence: N/A
EVALUATION EVIDENCE
Benchmarks
Only model-specific published scores are shown here. Missing values remain N/A and are not estimated from a composite score.
| Benchmark | Score | Status | |
|---|---|---|---|
| AutoBenchPublished Best for Work Automations (AutoBench) scores. | 15.5 | Published score | Data notes → |
| BrowseCompPublished Best in Browsing (BrowseComp) scores. | N/A | Not reported | Data notes → |
| SWE-Bench VerifiedPublished Best in Agentic Coding (SWE Bench) scores. | 88.6 | Published score | Data notes → |
| OSWorld-VerifiedPublished Best in Computer Use (OSWorld) scores. | N/A | Not reported | Data notes → |
| Humanity's Last ExamPublished Best Overall (Humanity's Last Exam) scores. | 57.9 | Published score | Data notes → |
PUBLISHED PRICING
Pricing and limits
Input / 1M tokens$5.00
Output / 1M tokens$25.00
Context window1000000
Knowledge cutoffN/A
LicenseProprietary
FIT CONTEXT
Best suited for
N/A
Capabilities: Text · Image · File · Tools · Reasoning. This is descriptive metadata, not a guarantee of task performance.
RANK HISTORY
How the record changed
No historical rank snapshots are recorded for this model.
RELATED RECORDS