Gemini 3.1 Flash Lite (Non-reasoning): benchmark results
Provider: Google. Released 2026-05-07. Access: API.
Aggregate Rating 1580 ± 19, rank #800 of 2205 rated models, from 25 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UAV-DualCog - Landmark Visibility Counting | 59.9 | Visibility-count accuracy (%; 1,024 flight videos in which t | 96.4 |
| UAV-DualCog - Self-Relative Position | 33.7 | Answer accuracy (%; 1,024 questions asking where the UAV is | 80 |
| German LLM Index - INCLUDE (139 questions) | 71.94 | Exact match (%) | 70.4 |
| German LLM Index - GermEval NER | 83.24 | seqeval micro-F1 excluding MISC (%) | 68.2 |
| German LLM Index - MuSR (564 questions) | 84.4 | Accuracy (%) | 66.7 |
| UAV-DualCog - Flight Behavior Recognition (Composite) | 22.8 | Composite-level behavior accuracy (%; 1,024 first-person UAV | 65.4 |
| German LLM Index - MMLU-ProX (11,759 questions) | 82.16 | Accuracy (%) | 63.6 |
| UAV-DualCog - Future Observation Prediction | 30.1 | Answer accuracy (%; 1,024 questions asking which view the UA | 61.8 |
| German LLM Index - ScaLA Acceptability | 74.21 | Matthews correlation coefficient (x100) | 55.8 |
| UAV-DualCog - Landmark-Relative Direction | 47.6 | Answer accuracy (%; 1,024 questions asking where a landmark | 55.7 |
| Hy-MultiTurn - Action Suppression | 56.2 | Importance-weighted score (%) on the 35 action suppression d | 47.6 |
| Hy-MultiTurn - Constraint Memory | 34.4 | Importance-weighted score (%) on the 34 constraint memory di | 28.6 |
Interactive version: theaggregate.ai/model?slug=gemini-3-1-flash-lite-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-13.