Mistral AI
Ministral 8B benchmark results
6 results on 6 benchmarks from 5 sources.
Also listed as: ministral-8b-2410 · Ministral-8B-Instruct-2410 (FC) · Ministral-8B-Instruct-2410 · mistralai/Ministral-8B-Instruct-2410
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1238 | 324 | Overall, style control on; 4781 votes; 95% CI 1229–1247“ministral-8b-2410” | Official leaderboard | Oct 8, 2026 |
| Open LLM Leaderboard v2 | 24.2% | 1776 | Average of 6 normalised benchmarks; bfloat16; 8.02B params“mistralai/Ministral-8B-Instruct-2410” | Official leaderboard | Mar 13, 2025 |
| GPQA Diamond | 27.1% | 269 | Epoch AI run, accuracy | Independent run | Jan 27, 2025 |
| MMLU-Pro | 37.9% | 196 | Overall accuracy; data source: TIGER-Lab; 8B“Ministral-8B-Instruct-2410” | Official leaderboard | Mar 11, 2026 |
| MATH Level 5 | 14.9% | 91 | Epoch AI run, accuracy | Independent run | Jan 27, 2025 |
| BFCL v4 (function calling) | 11.1% | 105 | Overall accuracy; native function calling (FC)“Ministral-8B-Instruct-2410 (FC)” | Official leaderboard | Oct 17, 2026 |
FAQ
Where do these Ministral 8B scores come from?
From Berkeley Function Calling Leaderboard (BFCL), Epoch AI Benchmarking Hub, 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.