Presumably because GLM 4.5 or Qwen3 comparisons would clobber them in eval score... | Hacker News

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

		bigyabai 5 months ago \| parent \| context \| favorite \| on: GPT-5 Presumably because GLM 4.5 or Qwen3 comparisons would clobber them in eval scores.

conradkay 5 months ago | [–]

You can check the same evals OpenAI used for those models

Hint: unclobbered

quotemstr 5 months ago | [–]

And don't require KYC crap to predict next token

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