Mistral: Mistral Small 3
Mistral Small 3 is an exceptionally affordable model with tool and function calling support, making it one of the best value options for lightweight business automation. Its reasoning benchmarks are modest, but for cost-sensitive, high-volume tasks it offers strong efficiency.
Assessment date: March 12, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment. The model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware. Read the blog post about the model here.
Capabilities
Architecture
| Modality | Text → Text |
| Tokenizer | Mistral |
| Parameters | 24B |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Evaluations
Benchmark data from Artificial Analysis and Hugging Face
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.05 | $0.000050 |
| Output | $0.08 | $0.000080 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
