Source? The most trusted benchmark right now (deepSWE) scores better or just as ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

bermudi 72 days ago | parent | context | favorite | on: ZCode – Harness for GLM-5.2

Source? The most trusted benchmark right now (deepSWE) scores better or just as well on their minimal harness than when using CC or codex

theshrike79 71 days ago [–]

deepSWE clearly doesn't need complex tool calling?

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact