Gemini 3.1 Flash Lite (High): benchmark results
Gemini 3.1 Flash Lite evaluated at the high reasoning-effort setting. Provider: Google. Released 2026-05-07. Access: API.
Aggregate Rating 1636 ± 15, rank #576 of 2170 rated models, from 60 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Korean CSAT 2026 (Easy Mode) - Korean | 100 | Points (out of 100) | 92.7 |
| SLR-Bench - Hard | 18 | Accuracy (%) | 88.2 |
| SLR-Bench - Easy | 96 | Accuracy (%) | 87.3 |
| SLR-Bench - Medium | 48 | Accuracy (%) | 87.3 |
| DGEval - Regulatory Recall | 22 | Accuracy (%) | 80.9 |
| Korean CSAT 2026 (Easy Mode) - Chemistry I | 48 | Points (out of 50) | 80.3 |
| Wolfram LLM Benchmarking Project | 58.1 | Correct Functionality (%) | 79.8 |
| DGEval - IMDG Code MCQ | 79 | Accuracy (%) | 79.4 |
| ObviousBench | 97.92 | Answer pass³ (%) | 77 |
| K-Bench - Risk | 93.31 | Risk Score (%, Default v1 prompt) | 72.1 |
| Korean CSAT 2026 (Easy Mode) - Total | 419.5 | Points (out of 450) | 65.3 |
| Korean CSAT 2026 (Easy Mode) - Physics I | 35 | Points (out of 50) | 63.7 |
Interactive version: theaggregate.ai/model?slug=gemini-3-1-flash-lite-high · How It Works · Data refreshed daily, snapshot 2026-11-05.