Gemini 2.5 Flash (Non-reasoning): benchmark results
Gemini 2.5 Flash evaluated with reasoning disabled. Provider: Google. Released 2025-06-17. Access: API.
Unified ELO 1566 ± 1, rank #862 of 3078 rated models, from 293 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| TIDE Trajectory - Sudoku - AUV | 60.4 | Area Under Variation (0-100) | 100 |
| EuroEval Spanish NLU - Sentiment Headlines ES | 52.95 | Sentiment classification Score (%) | 97.8 |
| EuroEval Bosnian | 62.35 | Average Score (%) | 97.6 |
| EuroEval Greek NLU - ScaLA EL | 57.72 | Linguistic acceptability Score (%) | 97.5 |
| EuroEval Danish Knowledge - Danish Citizen Tests | 98.35 | MCC (x100) | 96.9 |
| EuroEval Portuguese Common Sense Reasoning | 93.06 | Common Sense Reasoning Average Score (%) | 96.7 |
| EuroEval Serbian | 61.96 | Average Score (%) | 96.6 |
| EuroEval Albanian | 56.09 | Average Score (%) | 96.5 |
| EuroEval Norwegian Common Sense Reasoning | 88.29 | Common Sense Reasoning Average Score (%) | 96.3 |
| EuroEval Dutch | 73.91 | Average Score (%) | 95.9 |
| EuroEval Icelandic NLU - Hotter and Colder Sentiment | 58.32 | Sentiment classification Score (%) | 95.9 |
| EuroEval Danish Knowledge | 93.57 | Knowledge Average Score (%) | 95.8 |
Interactive version: theaggregate.ai/model?slug=gemini-2-5-flash-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-19.