Mistral Small 3.1 24B Instruct: benchmark results
Provider: Mistral. Released 2025-03-17. Access: Open.
Unified ELO 1526 ± 1, rank #568 of 1392 rated models, from 26 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MERA - ruDetox | 35.55 | Joint Score (%) | 92.8 |
| MERA - MultiQ | 56.87 | F1 (%) | 80.9 |
| LLM Stats (TriviaQA) | 80.5 | Score (%) | 79.4 |
| MERA - PARus | 91.2 | Accuracy (%) | 78.9 |
| MERA - ruTiE | 86.07 | Accuracy (%) | 78.7 |
| MERA - USE | 35.39 | Grade, normalized (%) | 73.2 |
| MERA - MaMuRAMu | 81.33 | Accuracy (%) | 72.2 |
| MERA - CheGeKa | 32.4 | F1 (%) | 71.3 |
| MERA - SimpleAr | 99.3 | EM (%) | 70.9 |
| MERA - ruOpenBookQA | 90.25 | Accuracy (%) | 70.8 |
| MERA - ruMMLU | 71.4 | Accuracy (%) | 68.9 |
| MERA - RCB | 56.39 | Accuracy (%) | 68.4 |
Interactive version: theaggregate.ai/model?slug=mistral-small-3-1-24b-instruct · How It Works · Data refreshed daily, snapshot 2026-09-05.