Devstral Small 2
Description
Devstral Small 1.1 (also called devstral-small-2507) is based on the Mistral-Small-3.1 foundation model and contains approximately 24 billion parameters. It supports a 128k token context window, which allows it to handle multi-file code inputs and long prompts typical in software engineering workflows. The model is fine-tuned specifically for structured outputs, including XML and function-calling formats. This makes it compatible with agent frameworks such as OpenHands and suitable for tasks like program navigation, multi-step edits, and code search. It is licensed under Apache 2.0 and available for both research and commercial use.
Capability Radar
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 276 | 32.0 | AA |
| General Ranking | 329 | 33.0 | AA |
| Math Reasoning | 246 | 35.0 | AA |
| Science | 331 | 34.0 | AA |
Benchmark Scores (LLM Stats)
Code
AA Evaluation Indices
LLM Stats Category Scores
Pricing
Speed
Provider Price Ranking
Provider Price Ranking
5 providers
Compare pricing across different API providers for this model.