Gemini 3.1 Pro (Preview) (Low): benchmark results
Gemini 3.1 Pro (Preview) evaluated at the low reasoning-effort setting. Provider: Google. Released 2026-02-19. Access: API.
Unified ELO 1669 ± 1, rank #183 of 1761 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ChessImageBench | 20.8 | All Correct (%) | 100 |
| Context Arena MRCR (4-needle) | 63.6 | AUC@1M (%) | 95.1 |
| Context Arena MRCR (2-needle) | 87.4 | AUC@1M (%) | 93.8 |
| Context Arena MRCR (8-needle) | 47 | AUC@1M (%) | 93.2 |
| LisanBench | 0.23 | Mean Path Length / Current Maximum | 86.9 |
| Epoch AI - Mystery Game Puzzles | 29 | Score | 79.4 |
| GIM | 1.45 | IRT ability (theta) | 77.8 |
| ALE-Bench | 1054.78 | Performance (Self-Refine x1) (self-reported) | 75 |
| NonoBench | 40 | Overall Accuracy (%) | 74.5 |
| OckBench | 79.5 | Accuracy (%) | 60 |
| MathArena - ARXIV February | 40.62 | Accuracy (%) | 52 |
| DeepResearchBench | 44.5 | Average Score | 25 |
Interactive version: theaggregate.ai/model?slug=gemini-3-1-pro-preview-low · How It Works · Data refreshed daily, snapshot 2026-09-05.