Would love to see the benchmark comparison between Mythos / Fable and GPT-5.5-Cy... | Hacker News

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

		GL26 2 days ago \| parent \| context \| favorite \| on: OpenAI DayBreak – GPT-5.5-Cyber Would love to see the benchmark comparison between Mythos / Fable and GPT-5.5-Cyber
		help

mijoharas 2 days ago [–]

Do you mean full benchmarks? Because from the article they claim 85.6 for 5.5-Cyber vs. 83.8 for mythos on Cybergym.

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