WebCompass-edit

Headlines · 1

1. 3d
   Co-Design Bench exposes gaps in real-world coding agents

   Alibaba researchers and researchers from several Asian universities built Co-Design Bench from real coding-change requests, including multimodal inputs such as images, audio, video, and documents. The paper reports that GPT-6 Astra led the ten tested models by satisfying about 70% of task requirements on average, but was fully correct in only 26.4% of tasks; performance also varied with the agent harness.

   The Decoder · 🔥 0

Experience and discussion from the community

Share my WebCompass-edit experienceAsk about WebCompass-edit