Mistral Small (Sep '24) — benchmark results
Provider: Mistral. Released 2024-09-17. Access: Open.
Unified ELO 1363 ± 45, rank #1424 of 1841 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA MATH-500 | 56.27 | Accuracy (%) | 19.4 |
| AA Humanity's Last Exam | 4.32 | Accuracy (%) | 18.9 |
| AA MMLU-Pro | 52.93 | Accuracy (%) | 16.6 |
| AA GPQA Diamond | 38.08 | Accuracy (%) | 15 |
| AA LiveCodeBench | 14.07 | Pass@1 (%) | 14.3 |
| Epoch AI - Scicode | 15.62 | Score | 14.2 |
| Artificial Analysis Intelligence Index | 4.66 | Intelligence Index | 13.7 |
Interactive version: theaggregate.ai/model?slug=mistral-small-sep-24 · How It Works · Data refreshed daily, snapshot 2026-07-25.