I don't know, but model names such as "kimi-k2-thinking" in the test set might o... | Hacker News

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

		tverbeure 19 hours ago \| parent \| context \| favorite \| on: “Car Wash” test with 53 models I don't know, but model names such as "kimi-k2-thinking" in the test set might offset a clue.

		help

etyhhgfff 14 hours ago [–]

Yes, there are some exceptions where it clearly states that a thinking model has been chosen like for kimi, but there is no such indicator for the GPT family from OpenAI and other major models.

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