TestingCatalog News 🗞· @testingcatalog · X·· 2026-05-08AI 评分49
AI 导读
Scale AI发布了SWE Atlas重构排行榜，这是一个评估智能体重构代码能力的新基准。 > 它要求智能体生成的代码行数是SWE Bench Pro的两倍。 > Claude Code with Opus 4.7位居榜首，其次是Codex with GPT-5.5、GPT-5.4和GPT-5.3。 > 重构对大型语言模型而言是相当重要的任务，因为这通常归结为相当枯燥的工程工作。
正文 · 原文
Scale AI published SWE Atlas Refactoring Leaderboard, a new benchmark that evaluates agent capabilities of restructuring the code.
It requires agents to produce twice as much lines of code than SWE Bench Pro.
Claude Code with Opus 4.7 tops the leaderboard followed by Codex with GPT-5.5, GPT-5.4 and GPT-5.3.
Refactoring is quite an important task for LLMs to handle as it often boils down to a quite boring engineering work.
来源：TestingCatalog News 🗞 · x.com