Mistral AI
Mixtral 8x7B benchmark results
9 results on 7 benchmarks from 5 sources.
Open weights Released: Dec 11, 2023 Updated Oct 22, 2026
Also listed as: mixtral-8x7b-instruct-v0.1 · Mixtral-8x7B-Instruct-v0.1 · open-mixtral-8x7b · Mixtral-8x7B-v0.1 · Mixtral 8x7b · mistralai/Mixtral-8x7B-Instruct-v0.1 · mistralai/Mixtral-8x7B-v0.1
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1197 | 347 | Overall, style control on; 73503 votes; 95% CI 1193–1201“mixtral-8x7b-instruct-v0.1” | Official leaderboard | Oct 8, 2026 |
| Open LLM Leaderboard v2 | 23.8% | 1884 | Average of 6 normalised benchmarks; bfloat16; 46.703B params“mistralai/Mixtral-8x7B-Instruct-v0.1” | Official leaderboard | Mar 13, 2025 |
| Open LLM Leaderboard v2 | 19.7% | 2741 | Average of 6 normalised benchmarks; float16; 46.703B params“mistralai/Mixtral-8x7B-v0.1” | Official leaderboard | Mar 13, 2025 |
| GPQA Diamond | 30.6% | 261 | Epoch AI run, accuracy | Independent run | Jan 27, 2025 |
| MMLU | 70.6% | 23 | Exact match; 5-shot | Paper / tech report via Epoch AI | Dec 11, 2023 |
| MMLU-Pro | 43.3% | 183 | Overall accuracy; data source: TIGER-Lab; 56B“Mixtral-8x7B-Instruct-v0.1” | Official leaderboard | Mar 11, 2026 |
| HumanEval / HumanEval+ | 45.1% | 77 | HumanEval (base tests), pass@1 greedy“Mixtral-8x7B-Instruct-v0.1” | Official leaderboard | Dec 26, 2024 |
| HumanEval / HumanEval+ | 39.6% | 76 | HumanEval+ (extended tests), pass@1 greedy“Mixtral-8x7B-Instruct-v0.1” | Official leaderboard | Dec 26, 2024 |
| MATH Level 5 | 9.3% | 99 | Epoch AI run, accuracy | Independent run | Jan 27, 2025 |
FAQ
Where do these Mixtral 8x7B scores come from?
From Epoch AI Benchmarking Hub, EvalPlus leaderboard, LMArena leaderboard dataset, 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.