Devstral (Mistral news) May 21, 2025
Devstral Small 1.0
Devstral Small 1.0.
4
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Mistral AI May 2025 Devstral Small 1.0
Open weights Small
No Epoch Capabilities Index score yet
- Multi-LCB 21.3% #10 /11
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SWE-bench Verified | 46.8% | #36 of 60 | Official leaderboard | |
| Multi-LCB | 21.3% | #10 of 11 | Official leaderboard | |
| AIRS-Bench | 0.18 | #5 of 5 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LisanBench | 40.0 | #127 of 133 | Official leaderboard |
Its lab's number next to a leaderboard
Where the benchmark's own leaderboard, or Epoch AI's run, also has this model. Gaps mostly come from different harnesses, effort levels and task subsets. Every pair.
| Benchmark | Lab says | Board says | Gap |
|---|---|---|---|
| SWE-bench Verified | 46.8% SWE-Bench Verified (OpenHands scaffold) | 46.8% Leaderboard, OpenHands | Same |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it.
Capabilities
- SWE-bench Verified 46.8