Mistral Small 3 — benchmark results
January 2025 Mistral Small 3 model row. Provider: Mistral. Released 2025-01-30. Access: Open.
Unified ELO 1527 ± 9, rank #693 of 1776 rated models, from 223 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Italian Common Sense Reasoning | 82.73 | Common Sense Reasoning Average Score (%) | 98.9 |
| EuroEval French Common Sense Reasoning | 83.43 | Common Sense Reasoning Average Score (%) | 98.8 |
| EuroEval German NLU - Sb10K | 62.27 | Sentiment classification Score (%) | 98.8 |
| MT-Bench PL - Extraction | 9.9 | Judge Score (0-10) | 96.9 |
| EuroEval English Common Sense Reasoning | 88.02 | Common Sense Reasoning Average Score (%) | 96.8 |
| EuroEval Spanish Common Sense Reasoning | 81.7 | Common Sense Reasoning Average Score (%) | 96.6 |
| EuroEval German Common Sense Reasoning | 82.04 | Common Sense Reasoning Average Score (%) | 96.4 |
| EuroEval Portuguese Common Sense Reasoning | 92.94 | Common Sense Reasoning Average Score (%) | 96.2 |
| EVALITA - lexical-substitution | 52.67 | CPS | 95.7 |
| EuroEval Swedish Common Sense Reasoning | 78.67 | Common Sense Reasoning Average Score (%) | 95.7 |
| EuroEval Spanish NLU - Sentiment Headlines ES | 51.95 | Sentiment classification Score (%) | 95.6 |
| EuroEval English | 76.05 | Average Score (%) | 94.3 |
Interactive version: theaggregate.ai/model?slug=mistral-small-3 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.