Introducing SWE-bench Verified
核心要点速览
We’re releasing a human-validated subset of SWE-bench that more reliably evaluates AI models’ ability to solve real-world software issues.
查看完整报道与分享
完整图文、背景资料与讨论归原始发布平台 OpenAI News 所有。
We’re releasing a human-validated subset of SWE-bench that more reliably evaluates AI models’ ability to solve real-world software issues.
完整图文、背景资料与讨论归原始发布平台 OpenAI News 所有。