Cognition 團隊發布 FrontierCode 2.0 程式碼評估基準
FrontierCode 2.02026.10.27FrontierCode 2.0 is a new generation of our FrontierCode benchmark: more diverse, challenging tasks from more repositories, graded by open-source maintainers on whether agent output is actually mergeable.
重點導讀
FrontierCode 2.0 是由 Cognition 團隊推出的新一代軟體工程AI 助理基準測試,旨在透過更嚴格的開源維護者審查標準,全面評估 AI 程式碼在真實專案中的可合併性與使用者體驗。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
信源出處cognition.ai
FrontierCode 2.02026.10.27FrontierCode 2.0 is a new generation of our FrontierCode benchmark: more diverse, challenging tasks from more repositories, graded by open-source maintainers on whether agent output is actually mergeable.
本文為 888news 精選之重點導讀。若需閱讀作者完整原文、技術細節與官方討論,請前往原始網站。
來源: Cognition / Devin Blog (cognition.ai)
開啟原文