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

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

This story was reported by 1 of the feeds we follow. Read the originals below — we link the source rather than rewriting it, so you can check the claim yourself.

• The Decoderthe-decoder.com/ai-coding-agents-still-need-human-cleanup-on