Mistral
Devstral Small 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 3Queryable facts extracted from the upstream model payload.
Rank #56 across 293 models.
Rank #455 across 474 models.
Rank #238 across 345 models.
Rank #320 across 478 models.
Percentile score by analysis domain.
Higher bars mean stronger relative placement.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 19.5 | #243 |
| Artificial Analysis Coding Index | coding | 20.7 | #189 |
| Artificial Analysis Math Index | math | 34.3 | #176 |
| MMLU-Pro | reasoning | 67.8% | #238 |
| reasoning |
| 53.2% |
| #320 |
| Humanity's Last Exam | reasoning | 3.4% | #455 |
| LiveCodeBench | coding | 34.8% | #199 |
| SciCode | coding, reasoning | 28.8% | #261 |
| Output Speed | speed | 72.5 tok/s | #174 |
| Time to First Token | speed | 0.53s | #56 |