真实测试：AI编码智能体近四分之三任务仍需人工收尾
原标题：AI coding agents still need human cleanup on nearly three out of four tasks in a real-world test
AI 摘要
阿里巴巴与多所亚洲高校的研究者构建了 Co-Design Bench 基准，用真实用户变更请求测试编码智能体。表现最好的 GPT-6 Astra 平均满足约 70% 的需求，但仅 26.4% 的任务完全正确，说明现有基准接近饱和、与现实可用性差距明显。研究还发现工作环境（harness）对结果影响与模型本身相当，建议排行榜同时报告模型与运行环境。
正文节选
AI coding agents still need human cleanup on nearly three out of four tasks in a real-world test Researchers from Alibaba and several Asian universities built a coding-agent benchmark from real user change requests. Even the best model fully completes only about one in four tasks, putting the near-perfect scores of older tests into perspective. The team developed Co-Design Bench, a new test for coding agents. The agents must rework existing web apps based on user requests, sometimes using images