Gemini 3.7 Flash (Low): benchmark results
Provider: Google. Released 2026-08-13. Access: API.
Unified ELO 1699 ± 1, rank #112 of 1761 rated models, from 24 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Law | 60.3 | Accuracy (%) | 97.7 |
| AA MMMU-Pro | 84.86 | Accuracy (%) | 97.3 |
| AA Omniscience - Business | 45.4 | Accuracy (%) | 94.2 |
| AA Omniscience - Humanities & Social Sciences | 53.7 | Accuracy (%) | 94.2 |
| AA-Omniscience Accuracy | 53.57 | Accuracy (%) | 94 |
| AA Omniscience | 22.13 | Score | 93.5 |
| AA Omniscience - Science, Engineering & Mathematics | 50.8 | Accuracy (%) | 93 |
| Artificial Analysis Intelligence Index | 41.06 | Intelligence Index | 90.8 |
| AA Omniscience - Software Engineering (SWE) | 69.5 | Accuracy (%) | 90.3 |
| AA GPQA Diamond | 90.1 | Accuracy (%) | 89.6 |
| AA Omniscience - Health | 41.7 | Accuracy (%) | 89.2 |
| AA Humanity's Last Exam | 35.13 | Accuracy (%) | 86.9 |
Interactive version: theaggregate.ai/model?slug=gemini-3-7-flash-low · How It Works · Data refreshed daily, snapshot 2026-09-05.