Know a great AI tool or AI news source? Submit it to AiByts
coding4 min read

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.

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

Read the full story

Originally published by The Decoder on Nov 8, 2026.

Read on The Decoder(opens in a new tab)

Comments

Sign in to join the discussion.

No comments yet — be the first to share your thoughts.