Mistral Small (2402): benchmark results
February 2024 Mistral Small API snapshot (mistral-small-2402). Provider: Mistral. Released 2024-02-26. Access: API.
Aggregate Rating 1446 ± 22, rank #1023 of 1656 rated models, from 103 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM MMLU - Public Relations | 77.27 | EM | 75 |
| HELM Lite - LegalBench - Abercrombie | 68 | Exact Match (%) | 70.6 |
| HELM Lite - MATH Level 1 - Prealgebra | 82.56 | Equivalent (CoT) (%) | 63.9 |
| HELM Lite - MATH Level 1 - Algebra | 85.93 | Equivalent (CoT) (%) | 62.2 |
| HELM Lite - MATH Level 1 - Counting and Probability | 69.23 | Equivalent (CoT) (%) | 58.3 |
| HELM Lite - MATH Level 1 - Geometry | 55.26 | Equivalent (CoT) (%) | 52.8 |
| MMLU | 68.7 | Accuracy (%) | 50.7 |
| BenchBench | 47.79 | Aggregate Score (%) | 50 |
| HELM MMLU - Econometrics | 61.4 | EM | 50 |
| HELM MMLU - Moral Scenarios | 57.54 | EM | 50 |
| HELM Lite - MATH Level 1 - Intermediate Algebra | 53.85 | Equivalent (CoT) (%) | 48.3 |
| HELM Lite - MATH Level 1 | 62.05 | Equivalent (CoT) (%) | 47.8 |
Interactive version: theaggregate.ai/model?slug=mistral-small-2402 · How It Works · Data refreshed daily, snapshot 2026-10-20.