BioMysteryBench Human-Difficult — leaderboard
Anthropic BioMysteryBench slice covering 23 real-world bioinformatics tasks no human benchmarker solved after QC, evaluated by average accuracy across five trials per problem.
Metric: Accuracy (self-reported). Source: benchmarklist.com. Status: saturation imminent. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Mythos 5 | 46.1 |
| 2 | Claude Opus 4.8 | 40 |
| 3 | Claude Mythos Preview | 29.6 |
| 4 | Claude Opus 4.7 | 24.7 |
| 5 | Claude Opus 4.6 | 23.5 |
| 6 | Claude Sonnet 4.6 | 19.1 |
| 7 | Claude Haiku 4.5 | 5.2 |
Interactive version: theaggregate.ai/benchmark?slug=biomysterybench-human-difficult · How the rankings work · Data refreshed daily, snapshot 2026-07-22.