BioMysteryBench Human-Solvable: leaderboard
Anthropic BioMysteryBench slice covering 76 real-world bioinformatics tasks solved by at least one human benchmarker, evaluated by average accuracy across five trials per problem.
Metric: Accuracy (self-reported). Source: benchmarklist.com. Status: years away from saturation. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5 | 90.1 |
| 2 | Gemini 3.8 Flash | 88.8 |
| 3 | Claude Sonnet 5 | 87.5 |
| 4 | Gemini 3.7 Flash | 87.1 |
| 5 | Claude Mythos 5 | 83.9 |
| 6 | GPT-5.6 Terra | 83.8 |
| 7 | Claude Mythos Preview | 82.6 |
| 8 | Gemini 3.6 Flash | 80.6 |
| 9 | Claude Opus 4.8 | 80.4 |
| 10 | GPT-5.6 Sol | 79.5 |
| 11 | Claude Opus 4.7 | 78.9 |
| 12 | Claude Opus 4.6 | 77.4 |
| 13 | Claude Sonnet 4.6 | 71.8 |
| 14 | Claude Haiku 4.5 | 36.8 |
Interactive version: theaggregate.ai/benchmark?slug=biomysterybench-human-solvable · How It Works · Data refreshed daily, snapshot 2026-09-05.