Co-Design Bench shows AI coding agents fully finish only about one in four real tasks
AIResearchers from Alibaba and several Asian universities built Co-Design Bench, a benchmark of real user change requests for coding agents. GPT-6 Astra, the best of ten models tested, meets about 70 percent of task requirements on average but is fully correct in only 26.4 percent of tasks.
Source details
The Decoder · Jonathan Kemper · the-decoder.comPublished · added here
Original title: AI coding agents still need human cleanup on nearly three out of four tasks in a real-world test