Ministral-3-8B-Instruct-2512: benchmark results
Mistral Ministral 3 8B Instruct 2512 snapshot. Provider: Mistral. Released 2025-12-02. Access: Open.
Aggregate Rating 1537 ± 9, rank #651 of 1640 rated models, from 451 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MATRIX (Materials Science) - EDS Interpretation | 47.5 | Judge score (% of the maximum) on MATRIX eds interpretation: | 100 |
| MATRIX (Materials Science) - SEM-BSE Interpretation | 48 | Judge score (% of the maximum) on MATRIX sem-bse interpretat | 100 |
| MATRIX (Materials Science) - SEM-SE Interpretation | 48.5 | Judge score (% of the maximum) on MATRIX sem-se interpretati | 100 |
| MATRIX (Materials Science) - TGA Interpretation | 54.5 | Judge score (% of the maximum) on MATRIX tga interpretation: | 100 |
| MATRIX (Materials Science) - XRD Interpretation | 49 | Judge score (% of the maximum) on MATRIX xrd interpretation: | 100 |
| EuroEval Slovene NLU - Sentinews | 56.34 | Sentiment classification Score (%) | 98.5 |
| EuroEval Polish Summarization - PSC | 25.67 | Score (%) | 98 |
| EuroEval French NLU - ScaLA FR | 68.28 | Linguistic acceptability Score (%) | 97.1 |
| EuroEval Lithuanian NLU - Atsiliepimai | 49.76 | Sentiment classification Score (%) | 96.5 |
| EuroEval French NLU - Allocine | 96.63 | Sentiment classification Score (%) | 96.1 |
| EuroEval Portuguese NLU - SST-2 PT | 86.78 | Sentiment classification Score (%) | 95.5 |
| EuroEval Bulgarian NLU - Cinexio | 59.43 | Sentiment classification Score (%) | 95.3 |
Interactive version: theaggregate.ai/model?slug=ministral-3-8b-instruct-2512 · How It Works · Data refreshed daily, snapshot 2026-10-13.