Exact model identity
Claude Code (Opus 4.6)
Anthropic · version status: reported
Similar model names are never merged automatically. Evaluation membership and numeric result rows only reference the exact ID
claude-code-opus-4-6.Evaluation settings
| Benchmark | Work | Run / group | Scope |
|---|---|---|---|
| CompBioBench | Agentic systems are adept at solving well-scoped, verifiable problems in computational biology | compbiobench-opus-full compbiobench-v1-opus-max-three-runs | full · n=100 |
| CompBioBench | Agentic systems are adept at solving well-scoped, verifiable problems in computational biology | compbiobench-opus-hardest compbiobench-v1-hardest-opus-max-three-runs | subset · n=17 |
Numeric results
| Benchmark | Work | Run / group | Metric | Value |
|---|---|---|---|---|
| CompBioBench | Agentic systems are adept at solving well-scoped, verifiable problems in computational biology | compbiobench-opus-full compbiobench-v1-opus-max-three-runs | Accuracy | 81 percent |
| CompBioBench | Agentic systems are adept at solving well-scoped, verifiable problems in computational biology | compbiobench-opus-full compbiobench-v1-opus-max-three-runs | Wall-clock time per question | 1101 seconds |
| CompBioBench | Agentic systems are adept at solving well-scoped, verifiable problems in computational biology | compbiobench-opus-full compbiobench-v1-opus-max-three-runs | Cost per question | 1.7 USD |
| CompBioBench | Agentic systems are adept at solving well-scoped, verifiable problems in computational biology | compbiobench-opus-hardest compbiobench-v1-hardest-opus-max-three-runs | Accuracy — difficulty Levels 4–5 | 69 percent |