They provide benchmarks in the paper https:// arxiv.org/abs/2606.21228 | Hacker News

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

irthomasthomas 78 days ago | parent | context | favorite | on: Asian AI startups launch Mythos-like models

They provide benchmarks in the paper https:// arxiv.org/abs/2606.21228

khurs 78 days ago [–]

Think 'indepenent' was implied when glimshe wrote 'reliable' benchmarks. Needs to be on the usual leaderboards.

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