Mistral AI
Mistral Small 3.2 benchmark results
6 results on 5 benchmarks from 3 sources.
Open weights Released: Jun 20, 2025 Updated Oct 22, 2026
Also listed as: mistral-small-2506 · mistral-small-3.2-2506 · Mistral-small-2506 (FC) · Mistral-Small-2506 (Prompt)
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1356 | 208 | Overall, style control on; 17466 votes; 95% CI 1351–1361“mistral-small-2506” | Official leaderboard | Oct 8, 2026 |
| LMArena Vision | 1140 | 117 | Overall, style control on; 10848 votes; 95% CI 1131–1149“mistral-small-2506” | Official leaderboard | Oct 2, 2026 |
| GPQA Diamond | 49.0% | 207 | Epoch AI run, accuracy | Independent run | Aug 28, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 30.3% | 192 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Aug 30, 2026 |
| BFCL v4 (function calling) | 37.1% | 51 | Overall accuracy; native function calling (FC)“Mistral-small-2506 (FC)” | Official leaderboard | Oct 17, 2026 |
| BFCL v4 (function calling) | 32.4% | 59 | Overall accuracy; prompt-based“Mistral-Small-2506 (Prompt)” | Official leaderboard | Oct 17, 2026 |
FAQ
Where do these Mistral Small 3.2 scores come from?
From Epoch AI Benchmarking Hub, Berkeley Function Calling Leaderboard (BFCL), and LMArena leaderboard dataset. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.