Google · model
Gemini 3.7 Flash (high) benchmark scores
As of 2026-10-07, Gemini 3.7 Flash (high) (Google) has measured scores on 2 benchmarks and estimated scores on 6 more.
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 94.5% | measured |
| CritPt | 24.5% | estimated ± 6.8 pp, medium confidence |
| τ³-Bench Banking | 49.0% | estimated ± 4.5 pp, low confidence |
| AA-AnalystAgent | 60.0% | measured |
| Harvey LAB | 93.7% | estimated ± 1.8 pp, medium confidence |
| Humanity's Last Exam | 49.4% | estimated ± 4.6 pp, high confidence |
| AutomationBench | 78.6% | estimated ± 11.2 pp, low confidence |
| EnterpriseOps-Gym | 56.7% | estimated ± 1.8 pp, low confidence |