# AI coding agents still need human cleanup on nearly three out of four tasks in a real-world test

> Source: <https://the-decoder.com/ai-coding-agents-still-need-human-cleanup-on-nearly-three-out-of-four-tasks-in-a-real-world-test/>
> Published: 2026-11-08 09:50:59+00:00

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](https://the-decoder.com/ai-coding-agents-still-need-human-cleanup-on-nearly-three-out-of-four-tasks-in-a-real-world-test/) appeared first on [The Decoder](https://the-decoder.com).