Devstral 2 (2512) — benchmark results
Provider: Mistral. Released 2025-12-09. Access: Open.
Unified ELO 1525 ± 55, rank #735 of 1841 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Boiling the Frog | 50.6 | Strict ASR (self-reported) | 75 |
| SnakeBench | 24.7 | TrueSkill Rating | 62.5 |
| AA-LCR | 30 | Score (self-reported) | 49.5 |
| CritPt | 0 | Accuracy (self-reported) | 30.3 |
| PrepBench | 33.3 | End-to-End Prep-Code Acc. (self-reported) | 22.2 |
| Arena AI Code | 1199 | Arena ELO (self-reported) | 6.3 |
| IOI | 0.67 | Score (self-reported) | 2.8 |
Interactive version: theaggregate.ai/model?slug=devstral-2-2512 · How It Works · Data refreshed daily, snapshot 2026-07-25.