Benchmark

BioMysteryBench

BioMysteryBench evaluates a model's ability to reason through challenging molecular biology problems, reporting performance on a hard subset and on the…

Modality
text
Categories
reasoning, science, biology
Openness
unknown
Source
llm_stats
Reported scores
3

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Claude Fable 5Anthropic0.4612026-06-09evidence
Claude Opus 5Anthropic0.9012026-07-24evidence
Gemini 3.7 FlashGoogle0.4352026-08-13evidence

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.