TestsBenchmarks · Reasoning
BioMysteryBench (human difficult)
Bioinformatics research workflows with tools; human-difficult split.
Measured by independent testersIndependent Reported by the makerVendor-reported
| Thinking levelSetting | |||||||
|---|---|---|---|---|---|---|---|
| 1 | Gemini 3.8 Flash | Google (Gemini / DeepMind) | 56.5% | Defaultdefault settings (API default thinking_level=medium) | Maker's own figureVendor-reportedGoogle ↗ | — | 2 Sep 2026 |
| 2 | Gemini 3.7 Flash | Google (Gemini / DeepMind) | 43.5% | Defaultdefault settings (API default thinking_level=medium) | Maker's own figureVendor-reportedGoogle ↗ | — | 13 Aug 2026 |
| 3 | Gemini 3.6 Flash | Google (Gemini / DeepMind) | 41.2% | Defaultdefault settings (API default thinking_level=medium) | Maker's own figureVendor-reportedGoogle ↗ | — | 13 Aug 2026 |