Devstral

Mistral AI's coding agent base model designed specifically for software engineering tasks. Features 24B parameters and 128K context window, optimized for multi-file editing, codebase exploration, and GitHub issue resolution. Supports deep integration with agent frameworks like OpenHands and SWE-Agent, understands complex relationships in large codebases, suitable for automated software development and code maintenance.

Intelligence(Relatively Weak)

Speed(Medium)

Input Supported Modalities

Is Reasoning Model

256,000

Context Window

128,000

Maximum Output Tokens

Knowledge Cutoff

Go Compare

Pricing

￥0.72 /M tokens

Input

￥2.16 /M tokens

Output

￥1.08 /M tokens

Blended Price

Quick Simple Comparison

Input

Output

Devstral

￥0.1

Devstral Medium

￥0.4

Devstral Small (May '25)

￥0.1

Basic Parameters

DevstralTechnical Parameters

Parameter Count

24,000.0M

Context Length

256.00k tokens

Training Data Cutoff

Open Source Category

Open Weights (Permissive License)

Multimodal Support

Text Only

Throughput

137

Release Date

2025-05-21

Response Speed

128.1,628 tokens/s

Benchmark Scores

Below is the performance of Devstral in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.

Intelligence Index

Large Language Model Intelligence Level

34.11

Large Language Model Intelligence Level

Coding Index

Indicator of AI model performance on coding tasks

25.18

Indicator of AI model performance on coding tasks

Math Index

Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks

37.53

Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks

MMLU Pro

Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video

63.2

Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video

GPQA

Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions

43.4

Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions

HLE

The model's comprehensive average score on the Hugging Face Open LLM Leaderboard

LiveCodeBench

Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems

25.8

Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems

SciCode

The model's capability in code generation for scientific computing or specific scientific domains

24.5

The model's capability in code generation for scientific computing or specific scientific domains

HumanEval

Score achieved by the AI model on the specific HumanEval benchmark test set

84.8

Score achieved by the AI model on the specific HumanEval benchmark test set

Math 500 Score

Score on the first 500 larger, more well-known mathematical benchmark tests

68.4

Score on the first 500 larger, more well-known mathematical benchmark tests

AIME Score

An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)

6.7

An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)

Output tokens/million

Output tokens/million

Output tokens/million

Output tokens/million

Output tokens/million

131k

Context Length

Gemini 2.0 Flash Lite (Preview)

Output tokens/million

Output tokens/million

33k

Context Length

Qwen2.5 Coder Instruct 32B

Output tokens/million

131k

Context Length

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご