Gemini 2.5 Flash (Preview 09-2025): benchmark results
September 2025 Gemini 2.5 Flash preview snapshot. Provider: Google. Released 2025-09-25. Access: API.
Aggregate Rating 1667 ± 24, rank #277 of 1656 rated models, from 75 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI Leaderboard | 50.35 | UGI Score | 89.4 |
| SpeechMap Compliance | 87.7 | % Requests Completed | 88.5 |
| SnakeBench | 30.8 | TrueSkill Rating | 88 |
| UGI - Natural Intelligence | 43.92 | NatInt Score | 86.5 |
| UGI - Writing | 44.88 | Writing Score | 83.6 |
| Chatbot Arena (Text - Japanese) | 1397 | Arena Score | 68.8 |
| Chatbot Arena (Text - Life, Physical & Social Science) | 1435 | Arena Score | 67.5 |
| Wolfram LLM Benchmarking Project | 51.9 | Correct Functionality (%) | 66.9 |
| Chatbot Arena (Text - Writing, Literature & Language) | 1394 | Arena Score | 66.7 |
| Chatbot Arena (Text - Legal & Government) | 1426 | Arena Score | 66.2 |
| Chatbot Arena (Text - Entertainment, Sports & Media) | 1380 | Arena Score | 65.8 |
| Chatbot Arena (Text - Creative Writing) | 1380 | Arena Score | 65.5 |
Interactive version: theaggregate.ai/model?slug=gemini-2-5-flash-preview-09-2025 · How It Works · Data refreshed daily, snapshot 2026-10-20.