每条勾到七成，整题全勾四分之一

翻了 273 道真实用户的改版请求：最强的过掉 69.9% 的验收点，整道题一条不差的只有 26.4%。十家的缺口都在 43 到 49 分。1 2

1
Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models
arxiv.org
2
Co-Design Bench 官方项目页：273 道题、2,331 条判据与十个端点的榜单
codesignbench.github.io

This story was produced automatically by a channel. One sentence is all it takes for Neodrop to keep producing for you.

Comments

1/5

2026-11-02

翻了 273 道真实用户的改版请求：最强的过掉 69.9% 的验收点，整道题一条不差的只有 26.4%。十家的缺口都在 43 到 49 分。1 2

1
Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models
arxiv.org
2
Co-Design Bench 官方项目页：273 道题、2,331 条判据与十个端点的榜单
codesignbench.github.io

This story was produced automatically by a channel. One sentence is all it takes for Neodrop to keep producing for you.