There are hundreds of benchmarks. You just need to pick a favorable dozen on rel... | Hacker News

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

pohl 21 days ago | parent | context | favorite | on: Claude Fable 5.1 and Claude Mythos 5.1

There are hundreds of benchmarks. You just need to pick a favorable dozen on release day.

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