Devstral 面向软件工程的智能体大语言模型发布

2025-05-21 00:00·408天前

AI 摘要

Mistral AI 与 All Hands AI 合作推出 Devstral，一款专注于解决真实世界 GitHub 问题的智能体大语言模型。该模型需在 OpenHands 或 SWE-Agent 等代码智能体框架中运行。在 SWE-Bench Verified 基准测试中，Devstral 获得 46.8% 的分数，超越此前的开源最先进模型超过 6 个百分点。在相同测试框架下，其表现优于 DeepSeek-V3-0324 和 Qwen3 232B-A22B，并且比闭源的 GPT-4.1-mini 高出超过 20%。Devstral 以 Apache 2.0 许可证开源，可在单张 RTX 4090 或配备 32GB 内存的 Mac 上本地部署，亦可通过 API 调用。

原文 · 未翻译

Today we introduce Devstral, our agentic LLM for software engineering tasks. Devstral is built under a collaboration between Mistral AI and All Hands AI 🙌, and outperforms all open-source models on SWE-Bench Verified by a large margin. We release Devstral under the Apache 2.0 license.

Agentic LLMs for software development

While typical LLMs are excellent at atomic coding tasks such as writing standalone functions or code completion, they currently struggle to solve real-world software engineering problems. Real-world development requires contextualising code within a large codebase, identifying relationships between disparate components, and identifying subtle bugs in intricate functions.

Devstral is designed to tackle this problem. Devstral is trained to solve real GitHub issues; it runs over code agent scaffolds such as OpenHands or SWE-Agent, which define the interface between the model and the test cases. Here, we show Devstral’s performance on the popular SWE-Bench Verified benchmark, a dataset of 500 real-world GitHub issues which have been manually screened for correctness.

Devstral achieves a score of 46.8% on SWE-Bench Verified, outperforming prior open-source SoTA models by more than 6% points. When evaluated under the same test scaffold (OpenHands, provided by All Hands AI 🙌), Devstral exceeds far larger models such as Deepseek-V3-0324 (671B) and Qwen3 232B-A22B.

In the table below, we also compare Devstral to closed and open models evaluated under any scaffold (including ones custom for the model). Here, we find that Devstral achieves substantially better performance than a number of closed-source alternatives. For example, Devstral surpasses the recent GPT-4.1-mini by over 20%.

Versatile: local deployment ↔️ enterprise use ↔️ copilots

Devstral is light enough to run on a single RTX 4090 or a Mac with 32GB RAM, making it an ideal choice for local deployment and on-device use. Coding platforms such as OpenHands can allow the model to interact with local codebases and provide fast resolution to issues. To try it yourself, view the documentation or tutorial video .

Mistral AI：News（网页）

63导出 Markdown

Devstral 面向软件工程的智能体大语言模型发布

2025-05-21 00:00·408天前

阅读原文· mistral.ai

AI 摘要

原文 · 保持原样，未翻译

Agentic LLMs for software development