AI IntelligenceNov 8, 2026AI Intelligence
Article
Alibaba's new Co-Design Bench tests AI coding agents on real user requests that previously tripped them up.
Even top performer GPT-6 Astra fully solves only 26.4 percent of tasks, while the same models score above 99 percent on older benchmarks.
AI-generated: summaries written by AI from the linked sources. How we use AI
AI-generatedSource: The Decoder
01
Source Brief
Alibaba's new Co-Design Bench tests AI coding agents on real user requests that previously tripped them up. Even top performer GPT-6 Astra fully solves only 26.4 percent of tasks, while the same models score above 99 percent on older benchmarks.
02