Claude Mythos 5.1: benchmark results
Anthropic September 2026 Mythos model for vetted cybersecurity and life-sciences users. Shares underlying weights with Fable 5.1 but uses different safeguards; benchmark results remain separately attributed. Provider: Anthropic. Released 2026-09-01. Access: Private.
Aggregate Rating 2008 ± 29, rank #2 of 1635 rated models, from 25 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ArXivMath June 2026 No Tools (Mythos 5.1 System Card) | 91.33 | Score (%) | 100 |
| ArXivMath June 2026 Tools (Mythos 5.1 System Card) | 93.88 | Score (%) | 100 |
| LatchBio SingleCellBench (Mythos 5.1 System Card) | 61.9 | Score (%) | 100 |
| LatchBio SpatialBench Verified (Mythos 5.1 System Card) | 77.6 | Score (%) | 100 |
| Organic Chemistry V2 (Mythos 5.1 System Card) | 69.2 | Score (%) | 100 |
| Protein Design Library Ranking (Mythos 5.1 System Card) | 49.3 | Score (%) | 100 |
| Protein Design Sequence Generation (Mythos 5.1 System Card) | 46 | Score (%) | 100 |
| ProteinGym Hard | 49.3 | Rank correlation (system card) | 100 |
| Protocols Troubleshooting (Mythos 5.1 System Card) | 70.2 | Score (%) | 100 |
| Vellum - Humanity's Last Exam | 65 | Accuracy (%) | 96.2 |
| Anthropic ECI - October 2026 Fit (Haiku 5.5 System Card) | 172.4 | AECI Score | 92.9 |
| LLM Stats Score | 44.14 | LLM Stats Score (conservative rating) | 87.8 |
Interactive version: theaggregate.ai/model?slug=claude-mythos-5-1 · How It Works · Data refreshed daily, snapshot 2026-11-05.