Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...
Gemini 2.5 thinking modelsRank #165 across 566
Rank #131 across 222
Rank #274 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 | 25.8 | #165 |
| Artificial Analysis Coding Index | coding | 33.3 | #131 |
| Artificial Analysis Math Index | math | 87.7 | #40 |
| MMLU-Pro | reasoning | 86.2% | #20 |
| reasoning |
| 84.4% |
| #95 |
| Humanity's Last Exam | reasoning | 21.1% | #98 |
| LiveCodeBench | coding | 80.1% | #28 |
| SciCode | coding, reasoning | 42.8% | #96 |
| MATH-500 | math | 96.7% | #29 |
| AIME | math | 88.7% | #10 |
| Output Speed | speed | 127.9 tok/s | #98 |
| Time to First Token | speed | 20.36s | #286 |
| Blended Price | cost | $3.44/M | #274 |
| Input Price | cost | $1.25/M | #245 |
| Output Price | cost | $10.00/M | #282 |
| Value Index | cost, overall | 7.5 | #275 |