Biology
LAB-Bench 2
Everyday tasks from a working biology lab — reading protocols, interpreting figures and sequence data, and answering the practical questions a researcher hits at the bench. Higher is better.
Rankings
Higher is betterLAB-Bench 2 — frequently asked questions
- What is LAB-Bench 2?
- Everyday tasks from a working biology lab — reading protocols, interpreting figures and sequence data, and answering the practical questions a researcher hits at the bench. Higher is better.
- Which AI model scores highest on LAB-Bench 2?
- Gemini 3.7 Flash by Google holds the best LAB-Bench 2 result among tracked models, at 82.1% (released Aug 13 2026). Higher scores are better on this benchmark.
- What are the top 1 models on LAB-Bench 2?
- 1. Gemini 3.7 Flash (Google) — 82.1%.
- How many models have a published LAB-Bench 2 score?
- 1 tracked model has a published LAB-Bench 2 score. Scores are the figures reported by each lab at that model's release, so this page is a record of results over time rather than a re-run leaderboard.