Devstral 面向软件工程的智能体大语言模型发布
阅读原文· mistral.aiMistral 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。
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.