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.
Unified ELO 1741 ± 35, rank #250 of 1806 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SLR-Bench - Hard | 18 | Accuracy (%) | 88.2 |
| SLR-Bench - Easy | 96 | Accuracy (%) | 87.3 |
| SLR-Bench - Medium | 48 | Accuracy (%) | 87.3 |
| SLR-Bench - Basic | 99 | Accuracy (%) | 62.7 |
| OTIS Mock AIME 2024-25 | 80 | Accuracy (%) | 60.3 |
| Chess Puzzles (Epoch AI) | 20 | Accuracy (%) | 47.9 |
| GIM | 0.1 | IRT ability (theta) | 47.8 |
| LLM2014 Logic 2026-03 | 33.87 | Median Score | 43.9 |
| LLM2014 Logic 2026-04 | 31.01 | Median Score | 35 |
| APEX-Agents | 25 | Mean Score (ReAct) (self-reported) | 32.6 |
| LLM2014 Logic 2026-06 | 18.81 | Median Score | 27.5 |
| LLM2014 Logic 2026-05 | 21.49 | Median Score | 21.1 |
Interactive version: theaggregate.ai/model?slug=gemini-3-1-flash-lite-high · How It Works · Data refreshed daily, snapshot 2026-08-07.