Mistral
Devstral Small (Jul '25)
Devstral Small (Jul '25) 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 3Operational Metrics
Output Speed194.2 tok/s
First Token0.39s
Blended Price$0.150/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseJul 10, 2025
Context Windown/a
Modalitiesn/a
Strength: TTFT
Rank #18 across 293 models.
0.39s
Strength: Input $
Rank #28 across 325 models.
$0.100/M
Strength: Speed
Rank #27 across 293 models.
194.2 tok/s
Watch Area: AIME
Rank #180 across 194 models.
0.3%
Watch Area: HLE
Rank #433 across 474 models.
3.7%
Watch Area: GPQA
Rank #384 across 478 models.
41.4%
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 15.2 | #309 |
| Artificial Analysis Coding Index | coding | 12.1 | #287 |
| Artificial Analysis Math Index | math | 29.3 | #187 |
| MMLU-Pro | reasoning | 62.2% | #263 |