BioMysteryBench Human Solvable (Fable/Mythos): leaderboard
BioMysteryBench Human Solvable results as reported in the Claude Fable 5 / Mythos 5 system card — Anthropic-run evaluation comparing a small set of frontier models.
Metric: Score (%). Source: www-cdn.anthropic.com. Saturation forecast: Around January 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Mythos 5 | 83.9 | #2 |
| 2 | Claude Mythos Preview | 82.6 | #4 |
| 3 | Claude Opus 4.8 | 80.4 | #37 |
| 4 | Claude Sonnet 4.6 | 78.4 | #90 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=biomysterybench-human-solvable-fable-mythos · How It Works · Data refreshed daily, snapshot 2026-10-20.