i'd interpret that as rounding error. that is unchanged swe-bench seems really h... | Hacker News

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

		usaar333 32 days ago \| parent \| context \| favorite \| on: Claude Opus 4.6 i'd interpret that as rounding error. that is unchanged swe-bench seems really hard once you are above 80%

Squarex 32 days ago [–]

it's not a great benchmark anymore... starting with it being python / django primarily... the industry should move to something more representative

usaar333 32 days ago | [–]

Openai has; they don't even mention score on gpt-5.3-codex.

On the other hand, it is their own verified benchmark, which is telling.

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