Benchmark
BioMysteryBench
What is BioMysteryBench?
Reported in two splits ("hard" and "human solved") that differ by more than 35 points, so a bare score is unreadable without its split. Anthropic notes its own…
- Released
- 2026-04-29
- Evaluates
- biology
- Openness
- unknown
- Importer
- Model reports
- Reported scores
- 1
Source provenance
- Original evidence https://huggingface.co/datasets/Anthropic/BioMysteryBench-full
BioMysteryBench links
BioMysteryBench results and reported scores
Model reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Hy4 preview | Tencent | 71.3 | 2026-08-28 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.
Which sources cite BioMysteryBench?
- Hy4 preview Tencent, 2026-08-28
- Claude Fable 5 and Mythos 5 Anthropic, 2026-06-09