Mistral Small 24B: benchmark results
Provider: Mistral.
Aggregate Rating 1521 ± 31, rank #2051 of 10916 rated models, from 24 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| RecoAtlas | 30 | Bundle SetHit@20 (self-reported) | 90.9 |
| The Compliance Gap | 100 | Authority (self-reported) | 90 |
| DiagFlowBench - Correct Abstention | 67.1 | Correct abstention (%): share of injected off-procedure oper | 66.7 |
| DiagFlowBench - Termination Recognition | 79.6 | Termination recognition (%): share of terminal-node turns at | 66.7 |
| HAERAE-Vision - Business/Economics | 22.29 | Checklist Score (%; original under-specified queries, GPT-5- | 45.5 |
| HAERAE-Vision - IT/Computer | 15.38 | Checklist Score (%; original under-specified queries, GPT-5- | 45.5 |
| HAERAE-Vision - Coding/Development | 16.36 | Checklist Score (%; original under-specified queries, GPT-5- | 43.2 |
| HAERAE-Vision - Machinery | 21.53 | Checklist Score (%; original under-specified queries, GPT-5- | 40.9 |
| HAERAE-Vision - Entertainment/Arts | 7.76 | Checklist Score (%; original under-specified queries, GPT-5- | 36.4 |
| HAERAE-Vision - Shopping/Consumer | 15.34 | Checklist Score (%; original under-specified queries, GPT-5- | 34.1 |
| HAERAE-Vision | 14.43 | Checklist Score (%; original under-specified queries, GPT-5- | 31.8 |
| HAERAE-Vision - Health/Medical | 25.07 | Checklist Score (%; original under-specified queries, GPT-5- | 31.8 |
Interactive version: theaggregate.ai/model?slug=mistral-small-24b · How It Works · Data refreshed daily, snapshot 2026-11-08.