Devstral Small 2
Devstral Small 2.
4
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Mistral AI Dec 2025 Devstral Small 2
Open weights
No Epoch Capabilities Index score yet
- SWE-bench Multilingual 55.7% #65 /73
- IOI (Vals) 2.50% #49 /55
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 | 56.4% | #32 of 60 | Official leaderboard | |
| SWE-bench Multilingual | 55.7% | #65 of 73 | Lab model card | |
| IOI (Vals) | 2.50% | #49 of 55 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Terminal-Bench 2.0 | 22.5% | #61 of 63 | Lab model card |
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 | 68% SWE-bench Verified | 56.4% Leaderboard, mini-SWE-agent | +12 pts |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.