Exact model identity
Claude Mythos Preview
Anthropic · version status: reported
Similar model names are never merged automatically. Evaluation membership and numeric result rows only reference the exact ID
claude-mythos-preview.Evaluation settings
| Benchmark | Work | Run / group | Scope |
|---|---|---|---|
| BioMysteryBench | Evaluating Claude's bioinformatics research capabilities with BioMysteryBench | biomysterybench-official-run biomysterybench-v8-full-five-episodes-protocol | full · n=99 |
| BioMysteryBench | Evaluating Claude's bioinformatics research capabilities with BioMysteryBench | biomysterybench-v8-human-difficult biomysterybench-v8-human-difficult-five-episodes | subset · n=23 |
| BioMysteryBench | Evaluating Claude's bioinformatics research capabilities with BioMysteryBench | biomysterybench-v8-human-solvable biomysterybench-v8-human-solvable-five-episodes | subset · n=76 |
Numeric results
| Benchmark | Work | Run / group | Metric | Value |
|---|---|---|---|---|
| BioMysteryBench | Evaluating Claude's bioinformatics research capabilities with BioMysteryBench | biomysterybench-v8-human-difficult biomysterybench-v8-human-difficult-five-episodes | Accuracy — human-difficult | 29.6 percent |
| BioMysteryBench | Evaluating Claude's bioinformatics research capabilities with BioMysteryBench | biomysterybench-v8-human-solvable biomysterybench-v8-human-solvable-five-episodes | Accuracy — human-solvable | 82.6 percent |