BioMysteryBench - Human Solvable
Science · 2026-07-24
BioMysteryBench Human Solvable contains problems that independent human experts were able to solve.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5 | 90.1 |
| Claude Mythos 5 | 89.0 |
| Opus 4.8 | 88.5 |
| Sonnet 5 | 87.5 |