Mistral-7B-v0.2: benchmark results
A community conversion of Mistral AI's 7B v0.2 base model into Hugging Face format, preserving the original weights released in December 2023. Provider: Mistral. Released 2023-12-06. Access: Open.
Aggregate Rating 1349 ± 18, rank #1388 of 1656 rated models, from 54 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EconLogicQA | 0.26 | Accuracy | 67.6 |
| Open Portuguese LLM - OAB Exams | 45.6 | Accuracy (%) | 61.4 |
| Open Portuguese LLM - BLUEX | 53.13 | Accuracy (%) | 55 |
| Open Portuguese LLM - ENEM | 62.7 | Accuracy (%) | 53 |
| Open LLM Leaderboard - GPQA | 29.19 | Score | 46.9 |
| Open LLM Leaderboard - MuSR | 40.32 | Score | 44.7 |
| Open Portuguese LLM - ASSIN2 RTE | 87.7 | Macro F1 (%) | 41.8 |
| BenchBench | 37.74 | Aggregate Score (%) | 36 |
| Open LLM Leaderboard - MMLU-Pro | 29.53 | Score | 34.9 |
| Open LLM Leaderboard - BBH | 45.1 | Score | 34.1 |
| BiGGen-Bench | 3.02 | Average Score (1-5) | 31.4 |
| Open Portuguese LLM - FaQuAD NLI | 47.7 | Macro F1 (%) | 30 |
Interactive version: theaggregate.ai/model?slug=mistral-7b-v0-2 · How It Works · Data refreshed daily, snapshot 2026-10-20.