Devstral Small (Jul '25): benchmark results
Provider: Mistral. Released 2025-07-10.
Aggregate Rating 1517 ± 35, rank #2100 of 10916 rated models, from 26 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Software Engineering (SWE) - JavaScript | 27.27 | Accuracy (%) | 48.3 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 16 | Accuracy (%) | 47.8 |
| AA Omniscience - Software Engineering (SWE) - Julia | 8 | Accuracy (%) | 46.1 |
| AA Omniscience - Software Engineering (SWE) - Rust | 44 | Accuracy (%) | 43 |
| Tau2-Bench Telecom | 28.36 | Success Rate (%) | 36.3 |
| AA Omniscience - Software Engineering (SWE) - TypeScript | 13.33 | Accuracy (%) | 36.2 |
| AA TAU-2 Bench | 28.36 | Accuracy (%) | 35.2 |
| AA Terminal-Bench Hard | 6.06 | Accuracy (%) | 33.9 |
| AA Omniscience - Software Engineering (SWE) - C | 25 | Accuracy (%) | 33.6 |
| AA Omniscience - Software Engineering (SWE) - Python | 13.5 | Accuracy (%) | 31.9 |
| AA AIME 2025 | 29.33 | Accuracy (%) | 30.3 |
| AA Omniscience - Software Engineering (SWE) - Swift | 24 | Accuracy (%) | 29.5 |
Interactive version: theaggregate.ai/model?slug=devstral-small-jul-25 · How It Works · Data refreshed daily, snapshot 2026-11-08.