# 真实测试显示：AI编程代理在近四分之三任务中仍需人工清理

> 全文为英语

**Published:** 2026年11月8日
**Author:** Jonathan Kemper
**Source:** The Decoder
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/ai-coding-agents-still-need-human-cleanup-on-nearly-three-out-of-four-ta

阿里巴巴新推出的编程代理基准测试Co-Design Bench，在已让AI代理在实践中翻车的真实用户需求上测试它们。即使表现最好的GPT-6 Astra，也仅能完全解决26.4%的任务。而在旧基准上，相同模型得分均超99%。这……

Alibaba's new coding-agent benchmark, Co-Design Bench, tests AI agents on real user requests that already tripped them up in practice. Even GPT-6 Astra, the top performer, fully solves only 26.4 percent of tasks. On older benchmarks, the same models score above 99 percent. The article AI coding agents still need human cleanup on nearly three out of four tasks in a real-world test appeared first on The Decoder.

---

*内容来自原始来源： [The Decoder](https://the-decoder.com/ai-coding-agents-still-need-human-cleanup-on-nearly-three-out-of-four-tasks-in-a-real-world-test/). 查看原文.*

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*