Mistral
Mistral Small 3.2 is a Mistral AI model profile from a lineup that spans compact Ministral models, specialist coding models, reasoning-oriented Magistral releases, and larger frontier open models. The local data makes its multilingual, coding, cost, and latency tradeoffs easier to compare against other providers.
Introducing Mistral 3Rank #350 across 566
Rank #194 across 222
Rank #39 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 | 10.6 | #350 |
| Artificial Analysis Coding Index | coding | 12.5 | #194 |
| Artificial Analysis Math Index | math | 27.0 | #192 |
| MMLU-Pro | reasoning | 68.1% | #244 |
| reasoning |
| 50.5% |
| #397 |
| Humanity's Last Exam | reasoning | 4.3% | #440 |
| LiveCodeBench | coding | 27.5% | #240 |
| SciCode | coding, reasoning | 26.4% | #361 |
| MATH-500 | math | 88.3% | #82 |
| AIME | math | 32.3% | #80 |
| Output Speed | speed | 144.9 tok/s | #80 |
| Time to First Token | speed | 0.40s | #17 |
| Blended Price | cost | $0.150/M | #39 |
| Input Price | cost | $0.100/M | #45 |
| Output Price | cost | $0.300/M | #43 |
| Value Index | cost, overall | 70.7 | #52 |