Devstral-2-123B-Instruct-2512: benchmark results
Provider: Mistral.
Aggregate Rating 1647 ± 51, rank #608 of 10870 rated models, from 4 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Twinkle Eval - TW-Legal Benchmark v1 | 51.04 | Accuracy (%) | 92.9 |
| Twinkle Eval - TMMLU+ | 72.32 | Accuracy (%) | 78.6 |
| Twinkle Eval - MMLU | 83.47 | Accuracy (%) | 71.4 |
| SWE-rebench | 42.01 | Resolved (%) | 47.9 |
Interactive version: theaggregate.ai/model?slug=devstral-2-123b-instruct-2512 · How It Works · Data refreshed daily, snapshot 2026-11-12.