Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...
Gemini 2.5 thinking modelsRank #221 across 566
No rank
Rank #170 across 371
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Higher bars mean stronger relative placement.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 20.1 | #221 |
| Artificial Analysis Math Index | math | 73.3 | #85 |
| MMLU-Pro | reasoning | 83.2% | #62 |
| GPQA | reasoning | 79.0% | #154 |
| Humanity's Last Exam |
| reasoning |
| 11.1% |
| #181 |
| LiveCodeBench | coding | 69.5% | #73 |
| SciCode | coding, reasoning | 39.4% | #156 |
| MATH-500 | math | 98.1% | #15 |
| AIME | math | 82.3% | #21 |
| Output Speed | speed | 219.1 tok/s | #26 |
| Time to First Token | speed | 9.93s | #265 |
| Blended Price | cost | $0.850/M | #170 |
| Input Price | cost | $0.300/M | #133 |
| Output Price | cost | $2.50/M | #193 |
| Value Index | cost, overall | 23.6 | #146 |