Ministral 3 3B — benchmark results

Mistral's 3B edge model from the Mistral 3 family, released under Apache 2.0 with image understanding and base, instruct and reasoning variants (December 2025). Provider: Mistral. Released 2025-12-02. Access: Open.

Unified ELO 1494 ± 10, rank #822 of 1776 rated models, from 336 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EuroEval Polish NLU - Polemo298.75Sentiment classification Score (%)100
EuroEval Catalan NLU - MultiWikiQA CA78.35Reading comprehension Score (%)99.1
EuroEval Estonian NLU - MultiWikiQA ET77.34Reading comprehension Score (%)98.8
EuroEval Icelandic NLU - NQII62.37Reading comprehension Score (%)98.2
EuroEval Catalan NLU - Guia CAT75.72Sentiment classification Score (%)98.1
EuroEval German NLU - Germanquad68.77Reading comprehension Score (%)96.9
EuroEval Finnish NLU - Tydiqa FI76.11Reading comprehension Score (%)96.2
EuroEval Slovene NLU - Sentinews54.45Sentiment classification Score (%)96.1
EuroEval Czech NLU - SQAD70.84Reading comprehension Score (%)95.6
EuroEval German Summarization - Mlsum DE38.47Score (%)95.3
EuroEval Catalan NLU - WikiANN CA74.81Named entity recognition Score (%)94.3
EuroEval Portuguese NLU - SST-2 PT85.31Sentiment classification Score (%)94.1

Interactive version: theaggregate.ai/model?slug=ministral-3-3b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.