Mistral Small 3
24B model rivaling GPT-4o mini, and larger models like Llama 3.3 70B. Ideal for chat use cases like customer support, translation and summarization.
About model
Mistral Small 3 is a 24B parameter large language model with state-of-the-art capabilities, suitable for fast response conversational agents, low latency function calling, and subject matter experts via fine-tuning. It is exceptionally knowledge-dense and supports dozens of languages. Ideal for hobbyists, organizations, and enterprises handling sensitive data.
Model | FrontierMath Tier 4 | GPQA Diamond | HLE | SciCode | GDPval-AA | Terminal-Bench 2.1 | Agent Arena | FrontierCode | DeepSWE |
|---|---|---|---|---|---|---|---|---|---|
Mistral Small 3 | 45.3% | Related open-source models | Competitor closed-source models | ||||||
 Claude Fable 5 | 87.8% | 92.6% | 53% | 60% | 62% | 85% | 53.5% | 70% | |
Claude Opus 5 | 73.2% | 93.2% | 53% | 56% | 68% | 89% | +16.4pp | 53.4% | 74% |
 GPT-5.6 Sol | 82.9% | 94.1% | 47% | 56% | 61% | 88% | 47.5% | 73% | |
 Grok 4.5 | 24.4% | 93.1% | 40% | 54% | 51% | 82% | +4.2pp | 42.4% | 54% |
GPT-5.6 Luna | 61.0% | 91.1% | 37% | 53% | 54% | 81% | 39.8% | 67% |
- TypeChat
- Main use casesChatMedium General PurposeFunction Calling
- FeaturesFunction Calling
- DeploymentDedicated
- Parameters24B
- Context length32K
- Input price
$0.10 / 1M tokens
- Output price
$0.30 / 1M tokens
- Input modalitiesText
- Output modalitiesText
- ReleasedJanuary 28, 2025
- Quantization levelFP16
- External link
- CategoryChat
