Mistral-Small-24B-Base-2501 — benchmark results
Mistral's 24B Apache-2.0 pretrained base behind Mistral Small 3, a knowledge-dense small model with a 32K context. Provider: Mistral. Released 2025-01-23. Access: Open.
Unified ELO 1456 ± 77, rank #968 of 1776 rated models, from 16 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - GPQA | 18.34 | Score | 96.8 |
| Open LLM Leaderboard - MMLU-Pro | 48.96 | Score | 96.7 |
| Open LLM Leaderboard - BBH | 48.54 | Score | 88.8 |
| Greek MMLU - Humanities | 74.07 | Accuracy (%) | 81.5 |
| Greek MMLU | 70.66 | Accuracy (%) | 79 |
| Open PL LLM - RAG | 69.99 | Average RAG Score (%) | 78.3 |
| Open PL LLM - Generative | 64.84 | Average Generative Score (%) | 78 |
| Greek MMLU - Other | 67.56 | Accuracy (%) | 77.8 |
| Greek MMLU - STEM | 67.6 | Accuracy (%) | 76.5 |
| Greek MMLU - Social Sciences | 73.55 | Accuracy (%) | 76.5 |
| Open PL LLM Leaderboard | 59.9 | Average Score (%) | 75.9 |
| Greek MMLU - Greek-Specific | 75.98 | Accuracy (%) | 74.1 |
Interactive version: theaggregate.ai/model?slug=mistral-small-24b-base-2501 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.