Mistral Small 3.2 24B — benchmark results
Provider: Mistral. Released 2025-06-20. Access: Open.
Unified ELO 1464 ± 37, rank #982 of 1841 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SnakeBench | 27.4 | TrueSkill Rating | 77.6 |
| PersonaArena | 3.75 | Average (self-reported) | 76.5 |
| AA-LCR | 17.3 | Score (self-reported) | 37.1 |
| Creative Writing v3 | 1211.5 | Elo score (self-reported) | 34.7 |
| EQ-Bench | 1112.6 | Normalized Elo (self-reported) | 32.9 |
| CritPt | 0 | Accuracy (self-reported) | 30.3 |
| Self-Driving Negotiator | 56 | Average success rate (%) | 30 |
| SuiChat-CN | 58.1 | Standard F1 (self-reported) | 25.6 |
| Qiskit QuantumKatas | 40 | Best (self-reported) | 20 |
| LisanBench | 0 | Mean Path Length / Current Maximum | 11.1 |
| FINESSE-Bench | 57.51 | exam-like (self-reported) | 10 |
| EQUITRIAGE | 35 | Exact% (self-reported) | 0 |
Interactive version: theaggregate.ai/model?slug=mistral-small-3-2-24b · How It Works · Data refreshed daily, snapshot 2026-07-25.