Gemini 3.1 Flash Lite (Low): benchmark results
Provider: Google. Released 2026-05-07. Access: API.
Aggregate Rating 1587 ± 28, rank #762 of 2170 rated models, from 16 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| DGEval - Regulatory Recall | 17.9 | Accuracy (%) | 70.6 |
| K-Bench - Risk | 92.89 | Risk Score (%, Default v1 prompt) | 63.9 |
| SLR-Bench - Easy | 76 | Accuracy (%) | 51.8 |
| SLR-Bench - Basic | 98 | Accuracy (%) | 50 |
| DGEval - IMDG Code MCQ | 66.3 | Accuracy (%) | 47.1 |
| K-Bench - Risk (Therapeutic v0) | 90.18 | Risk Score (%, Therapeutic v0 prompt) | 46.8 |
| Epoch AI - GPQA Diamond | 74.24 | Accuracy (%) | 46.7 |
| SLR-Bench - Medium | 13 | Accuracy (%) | 43.6 |
| SLR-Bench - Hard | 3 | Accuracy (%) | 42.7 |
| ObviousBench | 83.33 | Answer pass³ (%) | 33.3 |
| FrontierMath - Tiers 1-3 (v2) | 22.46 | Accuracy (%, 285 private v2 problems) | 31.3 |
| OTIS Mock AIME 2024-25 | 44.44 | Accuracy (%) | 30.5 |
Interactive version: theaggregate.ai/model?slug=gemini-3-1-flash-lite-low · How It Works · Data refreshed daily, snapshot 2026-11-05.