Mistral Nemo (2402): benchmark results
Provider: Mistral. Released 2024-07-18.
Aggregate Rating 1405 ± 24, rank #5831 of 10916 rated models, from 86 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Lite - MATH Level 1 - Precalculus | 66.67 | Equivalent (CoT) (%) | 62.8 |
| HELM Lite - MATH Level 1 - Geometry | 57.89 | Equivalent (CoT) (%) | 61.1 |
| HELM Lite - MATH Level 1 - Algebra | 85.19 | Equivalent (CoT) (%) | 58.3 |
| HELM MMLU - Computer Security | 81 | EM | 57.1 |
| HELM Lite - MATH Level 1 - Prealgebra | 79.07 | Equivalent (CoT) (%) | 55.6 |
| HELM Lite - MATH Level 1 - Counting and Probability | 66.67 | Equivalent (CoT) (%) | 55 |
| HELM Lite - MATH Level 1 | 66.85 | Equivalent (CoT) (%) | 54.4 |
| HELM Lite - GSM8K | 78.2 | Exact Match (%) | 52.8 |
| HELM Lite - MATH Level 1 - Number Theory | 56.67 | Equivalent (CoT) (%) | 52.8 |
| HELM MMLU - Virology | 56.02 | EM | 51.9 |
| HELM Lite - MATH Level 1 - Intermediate Algebra | 55.77 | Equivalent (CoT) (%) | 51.7 |
| HELM NarrativeQA | 73.1 | F1 (%) | 46.7 |
Interactive version: theaggregate.ai/model?slug=mistral-nemo-2402 · How It Works · Data refreshed daily, snapshot 2026-11-08.