Mistral
Mistral Small 3.1 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 #336 across 526
Rank #283 across 436
Rank #39 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 | 14.5 | #336 |
| Artificial Analysis Coding Index | coding | 13.9 | #283 |
| Artificial Analysis Math Index | math | 3.7 | #252 |
| MMLU-Pro | reasoning | 65.9% | #247 |
| reasoning |
| 45.4% |
| #386 |
| Humanity's Last Exam | reasoning | 4.8% | #345 |
| LiveCodeBench | coding | 21.2% | #266 |
| SciCode | coding, reasoning | 26.5% | #322 |
| MATH-500 | math | 70.7% | #140 |
| AIME | math | 9.3% | #139 |
| Output Speed | speed | 158.2 tok/s | #66 |
| Time to First Token | speed | 0.47s | #28 |
| Blended Price | cost | $0.138/M | #39 |
| Input Price | cost | $0.105/M | #59 |
| Output Price | cost | $0.235/M | #35 |
| Value Index | cost, overall | 105.1 | #51 |