Mistral AI
Mistral 7B v0.2 benchmark results
6 results on 5 benchmarks from 5 sources.
Open weights Released: Dec 11, 2023 Updated Oct 22, 2026
Also listed as: mistral-7b-instruct-v0.2 · Mistral-7B-Instruct-v0.2 · Mistral 7B · Mistral-7B-v0.2 · mistralai/Mistral-7B-Instruct-v0.2
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1149 | 376 | Overall, style control on; 19402 votes; 95% CI 1143–1156“mistral-7b-instruct-v0.2” | Official leaderboard | Oct 8, 2026 |
| Open LLM Leaderboard v2 | 18.5% | 2886 | Average of 6 normalised benchmarks; bfloat16; 7.242B params“mistralai/Mistral-7B-Instruct-v0.2” | Official leaderboard | Mar 13, 2025 |
| MMLU | 62.5% | 46 | Exact match; 5-shot | Paper / tech report via Epoch AI | Dec 11, 2023 |
| MMLU-Pro | 30.8% | 217 | Overall accuracy; data source: TIGER-Lab; 7B“Mistral-7B-Instruct-v0.2” | Official leaderboard | Mar 11, 2026 |
| HumanEval / HumanEval+ | 42.1% | 82 | HumanEval (base tests), pass@1 greedy“Mistral-7B-Instruct-v0.2” | Official leaderboard | Dec 26, 2024 |
| HumanEval / HumanEval+ | 36.0% | 81 | HumanEval+ (extended tests), pass@1 greedy“Mistral-7B-Instruct-v0.2” | Official leaderboard | Dec 26, 2024 |
FAQ
Where do these Mistral 7B v0.2 scores come from?
From EvalPlus leaderboard, LMArena leaderboard dataset, Epoch AI Benchmarking Hub, MMLU-Pro leaderboard (TIGER-Lab), and Hugging Face Open LLM Leaderboard v2 (archived). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.