Real-World Test: AI Coding Agents Need Cleanup on ~3 of 4 Tasks

Alibaba's new Co-Design Bench tests coding agents on real user requests that had already tripped them up. Top performer GPT-6 Astra fully solves only 26.4% of tasks, while the same models score above 99% on older benchmarks, highlighting a large gap between benchmarks and real-world use.

• Nous Research fine-tunes Qwen to strip political bias2026-11-07
• Nine AI agents fail expert bar on US national lab research questions2026-11-07
• NousResearch releases Arete-27B, a Qwen fine-tune2026-11-06
• Alibaba quietly announces Qwen 42026-11-06
• Moonshot's open-weight model tops OpenAI on financial research benchmark2026-11-06