Gemini 2.5 Flash (Preview 09-2025) (Non-reasoning): benchmark results
Provider: Google. Released 2025-09-25. Access: API.
Aggregate Rating 1612 ± 23, rank #691 of 2201 rated models, from 33 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI - Natural Intelligence | 43.6 | NatInt Score | 86.2 |
| AA MMLU-Pro | 83.61 | Accuracy (%) | 85.1 |
| UGI - Writing | 44.88 | Writing Score | 83.6 |
| AA Omniscience - Software Engineering (SWE) - R | 24 | Accuracy (%) | 83.4 |
| AA Omniscience - Software Engineering (SWE) - HTML | 46 | Accuracy (%) | 83.1 |
| UGI Leaderboard | 47.04 | UGI Score | 83 |
| AA Omniscience - Software Engineering (SWE) - Swift | 48 | Accuracy (%) | 82.4 |
| AA Omniscience - Software Engineering (SWE) - Java | 23 | Accuracy (%) | 81.7 |
| AA Omniscience - Software Engineering (SWE) - Go | 28 | Accuracy (%) | 80.7 |
| AA Omniscience - Software Engineering (SWE) - JavaScript | 39.09 | Accuracy (%) | 79.5 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 26 | Accuracy (%) | 76.6 |
| AA Omniscience - Software Engineering (SWE) - Python | 25 | Accuracy (%) | 72.9 |
Interactive version: theaggregate.ai/model?slug=gemini-2-5-flash-preview-09-2025-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-12.