Gemini 2.5 Flash is a thinking model that offers great, well-rounded capabilities. It is designed to offer a balance between price and performance with multimodal support and a 1M token context window.
Gemini 2.5 thinking modelsRank #237 across 526
Rank #232 across 436
Rank #184 across 357
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 | 20.6 | #237 |
| Artificial Analysis Coding Index | coding | 17.8 | #232 |
| Artificial Analysis Math Index | math | 60.3 | #117 |
| MMLU-Pro | reasoning | 80.9% | #95 |
| reasoning |
| 68.3% |
| #236 |
| Humanity's Last Exam | reasoning | 5.1% | #305 |
| LiveCodeBench | coding | 49.5% | #151 |
| SciCode | coding, reasoning | 29.1% | #278 |
| MATH-500 | math | 93.2% | #56 |
| AIME | math | 50.0% | #58 |
| Output Speed | speed | 185.1 tok/s | #41 |
| Time to First Token | speed | 0.56s | #60 |
| Blended Price | cost | $0.850/M | #184 |
| Input Price | cost | $0.300/M | #141 |
| Output Price | cost | $2.50/M | #200 |
| Value Index | cost, overall | 24.2 | #201 |