Gemini 2.5 Flash (Preview 09-2025) (Thinking): benchmark results
September 2025 Gemini 2.5 Flash preview snapshot evaluated with thinking enabled. Provider: Google. Released 2025-09-25. Access: API.
Aggregate Rating 1653 ± 28, rank #510 of 2168 rated models, from 28 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI Leaderboard | 50.35 | UGI Score | 89.4 |
| UGI - Natural Intelligence | 43.92 | NatInt Score | 86.5 |
| UGI - Writing | 43.88 | Writing Score | 82.5 |
| LegalBench | 82.63 | Score (%) | 60.9 |
| MMMU Pro | 80.75 | Score (%) | 58.8 |
| TaxEval v2 | 72.4 | Score (%) | 58 |
| MedQA | 91.17 | Score (%) | 57.4 |
| Vals AI MedQA | 91.17 | Accuracy (%) | 57.4 |
| Vals AI TaxEval v2 | 72.4 | Accuracy (%) | 56.2 |
| Vals AI LegalBench | 82.62 | Accuracy (%) | 56 |
| Vals AI MMMU | 80.75 | Accuracy (%) | 54.3 |
| MMLU Pro | 83.66 | Score (%) | 52.4 |
Interactive version: theaggregate.ai/model?slug=gemini-2-5-flash-preview-09-2025-thinking · How It Works · Data refreshed daily, snapshot 2026-10-20.