> Some sources mention that o3 scores 63.8 on SWE-bench, while Gemini 2.5 Pro sc... | Hacker News

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

		usaar333 9 months ago \| parent \| context \| favorite \| on: OpenAI o3 and o4-mini > Some sources mention that o3 scores 63.8 on SWE-bench, while Gemini 2.5 Pro scores 69.1. It's the opposite. o3 scores higher

SweetSoftPillow 9 months ago [–]

On SWE bench? Show your source.

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