Mistral AI
Mistral 7B v0.3 benchmark results
5 results on 5 benchmarks from 2 sources.
Open weights Released: Sep 27, 2023 Updated Oct 22, 2026
Also listed as: Mistral-7B-Instruct-v0.3 · open-mistral-7b · Mistral Instruct v0.3 (7B) · mistralai/Mistral-7B-Instruct-v0.3 · mistralai/Mistral-7B-v0.3
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| Open LLM Leaderboard v2 | 19.2% | 2799 | Average of 6 normalised benchmarks; bfloat16; 7.248B params“mistralai/Mistral-7B-Instruct-v0.3” | Official leaderboard | Mar 13, 2025 |
| GPQA Diamond | 15.2% | 279 | Epoch AI run, accuracy | Independent run | Jan 27, 2025 |
| MMLU | 59.9% | 72 | Exact match; 5-shot | Official leaderboard via Epoch AI | May 27, 2024 |
| AIME (OTIS Mock AIME 2024–2025) | 0.3% | 263 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Aug 30, 2026 |
| MATH Level 5 | 3.6% | 103 | Epoch AI run, accuracy | Independent run | Jan 27, 2025 |
FAQ
Where do these Mistral 7B v0.3 scores come from?
From Epoch AI Benchmarking Hub and Hugging Face Open LLM Leaderboard v2 (archived). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.