Benchmark is (finally) broken! | Hacker News

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

__mharrison__ 11 months ago | parent | context | favorite | on: Gemini 3.0 spotted in the wild through A/B testing

Benchmark is (finally) broken!

machiaweliczny 11 months ago [–]

Still doesn't understand physics as in that cover should be over the wheel, which should be easy if it used 2D space reasoning

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