Gemini 3.1 Flash Lite (Preview) (High): benchmark results
Gemini 3.1 Flash Lite (Preview) evaluated at the high reasoning-effort setting. Provider: Google. Released 2026-03-03. Access: API.
Aggregate Rating 1649 ± 25, rank #524 of 2168 rated models, from 20 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Vals AI SAGE | 49.54 | Accuracy (%) | 78.9 |
| Vals AI MedCode | 47.6 | Accuracy (%) | 70.1 |
| Vals AI LegalBench | 83.76 | Accuracy (%) | 68 |
| WeirdML | 52.19 | Average Score | 59.6 |
| ALE-Bench | 797.73 | Performance (Self-Refine x1) (imported) | 54.4 |
| Vals AI GPQA | 81.06 | Accuracy (%) | 52.6 |
| Vals AI TaxEval v2 | 71.79 | Accuracy (%) | 49.3 |
| Vals AI CorpFin v2 | 59.36 | Accuracy (%) | 40.6 |
| Vals AI Finance Agent | 46.12 | Accuracy (%) | 39.3 |
| Vals AI CaseLaw v2 | 54.98 | Accuracy (%) | 34.7 |
| Context Arena | 34.9 | Average Score (%) | 30.2 |
| o11y-bench - Pass@3 | 71.43 | Tasks passed on at least one of three attempts, Pass@3 (%) | 28.1 |
Interactive version: theaggregate.ai/model?slug=gemini-3-1-flash-lite-preview-high · How It Works · Data refreshed daily, snapshot 2026-10-20.