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) — September 27, 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 Gemini 3.8 Flash (88.8%). We do not use these results to rank models overall.
Claude Opus 5
Anthropic
Claude Opus 5.5
Anthropic
Gemini 3.8 Flash
4 modelsKnowledgeCurrentDisplay onlyUpdated September 27, 2026
Benchmark score table (4 models)
ScoreAmong the reported BioMysteryBench (human-solvable) rows, Claude Opus 5 is first at 90.1%. The third row is 1.3 points behind. The broader top-10 range is 3.0 points, so many of the published results sit in a relatively narrow band.
4 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)?
4 AI models have been evaluated on BioMysteryBench (human-solvable) on BenchLM.
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 2,000+ readers.
One email each week. Unsubscribe anytime.