Muse Wonder 高级工程师基准仅得 52%
disappointing showing for Muse Wonder on our senior engineer benchmark.
AI 导读
Muse Wonder 在我们的高级工程师基准上表现令人失望。 该基准要求模型从零重写一个 vibe coding 的烂代码库——能很好地衡量它在真实工程中的实用性 Muse Wonder 得 52%——远远落后于 event GPT-Sol 6.1 的 71% https://t.co/lyZsVCq2ng
主题
正文
当前显示原文，中文全文译文尚未就绪。
disappointing showing for Muse Wonder on our senior engineer benchmark.
it asks the model to rewrite a vibe coded slop codebase from scratch—good measure of its usefulness for real-world engineering
Muse Wonder gets 52%—far behind event GPT-Sol 6.1 at 71% https://t.co/lyZsVCq2ng