Ministral-3-14B-Reasoning-2512: benchmark results
Mistral Ministral 3 14B Reasoning 2512 snapshot. Provider: Mistral. Released 2025-12-02. Access: Open.
Aggregate Rating 1571 ± 13, rank #540 of 1656 rated models, from 360 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Bosnian NLU | 66 | NLU Average Score (%) | 100 |
| EuroEval Croatian NLU - Multi Wiki QA HR | 73.9 | Character F1 (%) | 100 |
| EuroEval Estonian NLU - MultiWikiQA ET | 77.98 | Character F1 (%) | 100 |
| EuroEval Serbian NLU - MultiWikiQA SR | 68.07 | Character F1 (%) | 100 |
| EuroEval Ukrainian NLU - MultiWikiQA UK | 71.57 | Character F1 (%) | 100 |
| EuroEval Bulgarian NLU - MultiWikiQA BG | 80.66 | Character F1 (%) | 99.5 |
| EuroEval French NLU - ScaLA FR | 73.6 | Matthews correlation coefficient (%) | 99.5 |
| EuroEval Italian NLU - SQuAD IT | 78.42 | Character F1 (%) | 99.5 |
| EuroEval Czech NLU - SQAD | 72.74 | Character F1 (%) | 99.1 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 79.73 | Character F1 (%) | 99.1 |
| EuroEval Albanian NLU - MultiWikiQA SQ | 70.23 | Character F1 (%) | 99 |
| EuroEval Hungarian NLU - MultiWikiQA HU | 71.83 | Character F1 (%) | 99 |
Interactive version: theaggregate.ai/model?slug=ministral-3-14b-reasoning-2512 · How It Works · Data refreshed daily, snapshot 2026-10-20.