BioMysteryBench contains 99 expert-authored bioinformatics research questions over messy real-world datasets. Agents may use a Linux terminal, bioinformatics software, Python and R, plus restricted access to canonical data sources; answers are graded on objective biological conclusions rather than a prescribed analysis path.
Browse the latest scores, model modes, release dates, and parameter sizes for BioMysteryBench.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
No benchmark data available yet
Google reported Gemini 3.7 Flash at 87.1% on the 76 human-solvable tasks and 43.5% on the 23 human-difficult tasks in August 2026.
