BioMysteryBench - Human Difficult
Science · 2026-07-24
BioMysteryBench Human Difficult contains problems that remain unsolved by independent human experts but have objective ground-truth solutions.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5 | 49.4 |
| Claude Mythos 5 | 46.5 |
| Opus 4.8 | 42.4 |
| Sonnet 5 | 34.1 |