Gemini 2.5 Flash-Lite is a balanced, low-latency model with configurable thinking budgets and tool connectivity (e.g., Google Search grounding and code execution). It supports multimodal input and offers a 1M-token context window.
Gemini 2.5 thinking modelsRank #280 across 526
Rank #346 across 436
Rank #59 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 | 17.6 | #280 |
| Artificial Analysis Coding Index | coding | 9.5 | #346 |
| Artificial Analysis Math Index | math | 53.3 | #135 |
| MMLU-Pro | reasoning | 75.9% | #168 |
| reasoning |
| 62.5% |
| #278 |
| Humanity's Last Exam | reasoning | 6.4% | #244 |
| LiveCodeBench | coding | 59.3% | #119 |
| SciCode | coding, reasoning | 19.3% | #387 |
| MATH-500 | math | 96.9% | #28 |
| AIME | math | 70.3% | #39 |
| Output Speed | speed | 265.2 tok/s | #15 |
| Time to First Token | speed | 17.93s | #279 |
| Blended Price | cost | $0.175/M | #59 |
| Input Price | cost | $0.100/M | #41 |
| Output Price | cost | $0.400/M | #60 |
| Value Index | cost, overall | 100.6 | #56 |