Devstral Small (2507): benchmark results
Provider: Mistral. Released 2025-07-10.
Aggregate Rating 1503 ± 43, rank #2305 of 10916 rated models, from 5 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| DataGovBench - Table QA | 15.2 | Question-set accuracy (%; 211 simple and decomposable questi | 55.6 |
| Wolfram LLM Benchmarking Project | 35.3 | Correct Functionality (%) | 36 |
| Design Arena (Website) | 800 | Elo | 1.5 |
| Design Arena (UI Components) | 834 | Elo | 1.1 |
| Design Arena (Game Dev) | 777 | Elo | 0.5 |
Interactive version: theaggregate.ai/model?slug=devstral-small-2507 · How It Works · Data refreshed daily, snapshot 2026-11-08.