Mistral AI
Comparing 6 models from Mistral AI.
| Model | Total ▼ | Released | Context | Size | Creative writing | Rule following | Utility | Mathematics | Tooling | Language | Logic |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Mistral Large 2 | 65.49% | Jul 24, 24 | 128k | – | 24.18% | 43.02% | 78.67% | 85.00% | 75.00% | 82.86% | 79.38% |
| Mistral Small Creative | 61.86% | Dec 16, 25 | 32k | – | 20.92% | 56.71% | 70.33% | 100.00% | 61.54% | 49.86% | 90.00% |
| Mistral NeMO | 57.42% | Jul 18, 24 | 128k | – | 27.72% | 30.48% | 67.56% | 95.00% | 68.21% | 76.89% | 78.75% |
| Mistral Large | 55.68% | Feb 26, 24 | 32k | – | 38.82% | 47.96% | 56.00% | 50.00% | 54.23% | 85.78% | 60.62% |
| Ministral 8B | 44.63% | Oct 16, 24 | 128k | – | 17.87% | 30.57% | 52.17% | 40.00% | 48.08% | 51.51% | 67.50% |
| Ministral 3B | 44.40% | Oct 16, 24 | 128k | – | 18.62% | 29.95% | 53.50% | 40.00% | 52.31% | 41.23% | 65.63% |
Model Performance
Cost vs Performance
Compares total benchmark cost against overall score for Mistral AI models. Quadrant lines are drawn at the median values.