BioMysteryBench Verified - Human Difficult (Anthropic): leaderboard
Anthropic system-card run of BioMysteryBench Verified human-difficult tasks, testing hard biological mystery problem solving.
Metric: Score (%). Source: www-cdn.anthropic.com. Saturation forecast: Around 2029. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 40 | #37 |
| 2 | Claude Mythos Preview | 29.6 | #4 |
| 3 | Claude Opus 4.7 | 24.7 | #49 |
| 4 | Claude Sonnet 4.6 | 19.1 | #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-verified-human-difficult-anthropic · How It Works · Data refreshed daily, snapshot 2026-10-20.