Mistral Small 3.2: benchmark results
Mistral Small 3.2, a 24B refinement of Small 3.1 (June 2025). Provider: Mistral. Released 2025-06-20. Access: Open.
Unified ELO 1512 ± 1, rank #635 of 1392 rated models, from 658 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Ukrainian NLU | 60.27 | NLU Average Score (%) | 100 |
| EuroEval Albanian NLU - MultiWikiQA SQ | 70.5 | Reading comprehension Score (%) | 99.5 |
| EuroEval Slovak NLU | 62.65 | NLU Average Score (%) | 99.5 |
| EuroEval Slovak NLU - Multi Wiki QA SK | 74.36 | Reading comprehension Score (%) | 99.5 |
| EuroEval Slovene NLU - MultiWikiQA SL | 76.44 | Reading comprehension Score (%) | 99.5 |
| EuroEval Danish NLU - Multi Wiki QA DA | 82.73 | Reading comprehension Score (%) | 99.3 |
| EuroEval Faroese NLU - FoQA | 79.92 | Reading comprehension Score (%) | 99.2 |
| EuroEval Swedish NLU - Multi Wiki QA SV | 81.73 | Reading comprehension Score (%) | 99.2 |
| EuroEval Bulgarian NLU - MultiWikiQA BG | 79.74 | Reading comprehension Score (%) | 99.1 |
| EuroEval German NLU - Sb10K | 62.28 | Sentiment classification Score (%) | 99.1 |
| EuroEval Latvian NLU - MultiWikiQA LV | 72.5 | Reading comprehension Score (%) | 99.1 |
| EuroEval Bosnian NLU - Multi Wiki QA BS | 76.45 | Reading comprehension Score (%) | 99 |
Interactive version: theaggregate.ai/model?slug=mistral-small-3-2 · How It Works · Data refreshed daily, snapshot 2026-09-05.