Ministral 3 8B — benchmark results
Mistral's Apache-2.0 8B dense edge model from the Mistral 3 family, with image understanding (December 2025). Provider: Mistral. Released 2025-12-02. Access: Open.
Unified ELO 1535 ± 7, rank #661 of 1776 rated models, from 649 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Finnish NLU - Tydiqa FI | 77.99 | Reading comprehension Score (%) | 99.7 |
| EuroEval Estonian NLU - MultiWikiQA ET | 77.4 | Reading comprehension Score (%) | 99.2 |
| EuroEval Croatian NLU - MMS HR | 48.41 | Sentiment classification Score (%) | 99.1 |
| EuroEval Icelandic NLU - NQII | 63.52 | Reading comprehension Score (%) | 98.4 |
| EuroEval Polish NLU - Polemo2 | 97.11 | Sentiment classification Score (%) | 98.3 |
| EuroEval Italian NLU - SQuAD IT | 76.39 | Reading comprehension Score (%) | 98.1 |
| EuroEval German Summarization - Mlsum DE | 39.57 | Score (%) | 98 |
| EuroEval Dutch NLU - SQuAD NL | 84.01 | Reading comprehension Score (%) | 97.8 |
| AGC-Bench - mops | 1.99 | Dataset z-score | 97.6 |
| AGC-Bench - schnovel | 1.63 | Dataset z-score | 97.6 |
| EuroEval Czech NLU - CSFD Sentiment | 67.56 | Sentiment classification Score (%) | 97.4 |
| EuroEval Catalan NLU - WikiANN CA | 77.83 | Named entity recognition Score (%) | 97.2 |
Interactive version: theaggregate.ai/model?slug=ministral-3-8b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.