ModelSWE-1.7模型

SWE-1.7

专门针对软件工程任务优化的大语言模型，宣称在编程智能水平上接近GPT-5.5和Claude Opus的表现，属于SWE系列专用编程模型

Timeline (last 90 days)

Sep 13

When completing the same tasks, SWE-2 requires 58% fewer interaction turns than its predecessor SWE-1.7, costs 81% less, and achieves a higher score.

Unverified50%

When completing the same tasks, SWE-2 requires 58% fewer interaction turns than its predecessor SWE-1.7, costs 81% less, and achieves a higher score.