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

BenchmarkScoreMetricPercentile
EuroEval Finnish NLU - Tydiqa FI77.99Reading comprehension Score (%)99.7
EuroEval Estonian NLU - MultiWikiQA ET77.4Reading comprehension Score (%)99.2
EuroEval Croatian NLU - MMS HR48.41Sentiment classification Score (%)99.1
EuroEval Icelandic NLU - NQII63.52Reading comprehension Score (%)98.4
EuroEval Polish NLU - Polemo297.11Sentiment classification Score (%)98.3
EuroEval Italian NLU - SQuAD IT76.39Reading comprehension Score (%)98.1
EuroEval German Summarization - Mlsum DE39.57Score (%)98
EuroEval Dutch NLU - SQuAD NL84.01Reading comprehension Score (%)97.8
AGC-Bench - mops1.99Dataset z-score97.6
AGC-Bench - schnovel1.63Dataset z-score97.6
EuroEval Czech NLU - CSFD Sentiment67.56Sentiment classification Score (%)97.4
EuroEval Catalan NLU - WikiANN CA77.83Named 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.