Gemini 2.5 Flash (Thinking): benchmark results
Gemini 2.5 Flash evaluated with thinking enabled. Provider: Google. Released 2025-06-17. Access: API.
Unified ELO 1592 ± 1, rank #466 of 1761 rated models, from 297 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Catalan | 68.12 | Average Score (%) | 100 |
| EuroEval Slovene NLU | 63.65 | NLU Average Score (%) | 100 |
| MedLayXPlain | 70.6 | S (self-reported) | 100 |
| EuroEval Polish | 68.33 | Average Score (%) | 99.6 |
| EuroEval Romanian | 70.53 | Average Score (%) | 99.5 |
| EuroEval Serbian | 70 | Average Score (%) | 99.5 |
| EuroEval Slovak Common Sense Reasoning | 74.26 | Common Sense Reasoning Average Score (%) | 99.5 |
| EuroEval Slovene NLU - ScaLA SL | 64.71 | Linguistic acceptability Score (%) | 99.5 |
| EuroEval Swedish NLU - ScaLA SV | 75.22 | Linguistic acceptability Score (%) | 99.3 |
| EuroEval Czech | 67.83 | Average Score (%) | 99.1 |
| EuroEval Czech NLU - CS GEC | 63.31 | Linguistic acceptability Score (%) | 99.1 |
| EuroEval Latvian NLU - ScaLA LV | 56.6 | Linguistic acceptability Score (%) | 99.1 |
Interactive version: theaggregate.ai/model?slug=gemini-2-5-flash-thinking · How It Works · Data refreshed daily, snapshot 2026-09-05.