what? nobody looks at those benchmarks, you use whatever works for your task, in... | Hacker News

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

PunchTornado on July 10, 2025 | parent | context | favorite | on: Grok 4 Launch [video]

what? nobody looks at those benchmarks, you use whatever works for your task, in most cases either gemini or claude. those benchmarks don't mean anything as models overfit on them.

esafak on July 10, 2025 [–]

Come on, the benchmarks do mean something, even if companies overfit them. Models are indisputably improving together with their benchmark scores.

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