BioMysteryBench Human Solvable (BioMysteryBench (human-solvable))
We show this table for reference; we do not rank on it.
Computational biology challenges that independent human experts were able to solve.
Benchmark score on BioMysteryBench (human-solvable) — November 13, 2026
We compile the BioMysteryBench (human-solvable) rows from provider self-reports. Claude Opus 5 leads the table at 90.1%, followed by Claude Opus 5.5 (89.3%) and Claude Sonnet 5.5 (89.2%). We do not use these results to rank models overall.
Claude Opus 5
Anthropic
Reported by AnthropicClaude Opus 5.5
Anthropic
Reported by AnthropicClaude Sonnet 5.5
Anthropic
Reported by Anthropic5 modelsKnowledgeCurrentDisplay onlyUpdated November 13, 2026
Benchmark score table (5 models)
All 5 results on this page were reported by the labs that built the models.
| Rank | Model / configuration | Score | Who ran it | Parameters (B) | Open / closed |
|---|---|---|---|---|---|
| 1 | Claude Opus 5AnthropicReported by Anthropic | 90.1% | Reported by Anthropic | Not reported | Closed |
| 2 | Claude Opus 5.5AnthropicReported by Anthropic | 89.3% | Reported by Anthropic | Not reported | Closed |
| 3 | Claude Sonnet 5.5AnthropicReported by Anthropic | 89.2% | Reported by Anthropic | Not reported | Closed |
| 4 | Gemini 3.8 FlashGoogleReported by Google | 88.8% | Reported by Google | Not reported | Closed |
| 5 | Gemini 3.7 FlashGoogleReported by Google | 87.1% | Reported by Google | Not reported | Closed |
- Lab-reported
- Benchmark-run
- Independent
Among the reported BioMysteryBench (human-solvable) rows, Claude Opus 5 is first at 90.1%. The third row is 0.9 points behind. The broader top-10 range is 3.0 points, so many of the published results sit in a relatively narrow band.
5 models have been evaluated on BioMysteryBench (human-solvable). The benchmark falls in the Knowledge category. BioMysteryBench (human-solvable) is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About BioMysteryBench (human-solvable)
Year
2026
Tasks
Human-solvable computational biology investigations
Format
Task score
Difficulty
Expert computational biology
Section 8.17.1 reports the provider's revised human-solvable subset after removing three problems based on external feedback.
Freshness and provenance
Version
BioMysteryBench (human-solvable) 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does BioMysteryBench (human-solvable) measure?
Computational biology challenges that independent human experts were able to solve.
Which model scores highest on BioMysteryBench (human-solvable)?
Claude Opus 5 by Anthropic currently leads with a score of 90.1% on BioMysteryBench (human-solvable).
How many models are evaluated on BioMysteryBench (human-solvable)?
5 AI models have published results on BioMysteryBench (human-solvable) in the BenchLM catalog.
Compare top models on BioMysteryBench (human-solvable)
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.