reasoning benchmark
BioMysteryBench Leaderboard
BioMysteryBench evaluates a model's ability to reason through challenging molecular biology problems.
Updated Sep 5, 2026
Models5
Model coverage5
MetricScore
EvidenceB
BioMysteryBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Score90.10% | Percentile100.00% | Participants5 | EvidenceC | Evaluated |
| Rank02 | ModelTE | Score71.30% | Percentile75.00% | Participants5 | EvidenceC | Evaluated |
| Rank03 | ModelGO | Score56.50% | Percentile50.00% | Participants5 | EvidenceC | Evaluated |
| Rank04 | ModelAN | Score46.10% | Percentile25.00% | Participants5 | EvidenceC | Evaluated |
| Rank05 | ModelGO | Score43.50% | Percentile0.00% | Participants5 | EvidenceC | Evaluated |
BioMysteryBench Highlights
The leading models and scores on this benchmark.
BioMysteryBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for BioMysteryBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is BioMysteryBench?
What BioMysteryBench measures and how its scores work.
BioMysteryBench is a reasoning benchmark for challenging molecular biology problems.
It measures performance on a hard subset and on the subset of problems solved by human experts, reported as a Score ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- BioMysteryBench
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about BioMysteryBench.
Which model scores highest on BioMysteryBench?
Claude Opus 5 is currently ranked first with 90.10%.
What are the top three models on BioMysteryBench?
The current leaders are Claude Opus 5 (90.10%), Hy4 preview (71.30%), and Gemini 3.8 Flash (56.50%).
Which BioMysteryBench model has the lowest official input price?
Gemini 3.8 Flash has the lowest matched official input price at $0.75 input / $3.8 output per 1M tokens.
Which models are fastest among BioMysteryBench results?
The fastest matched records are Gemini 3.7 Flash (117.86 tok/s via Google), Claude Opus 5 (62.88 tok/s via Anthropic), and Gemini 3.8 Flash (51.56 tok/s via Google).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.