I would love to see how well Deepseek V3 do on this. | Hacker News

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

		rubymamis 11 months ago \| parent \| context \| favorite \| on: 30% drop in O1-preview accuracy when Putnam proble... I would love to see how well Deepseek V3 do on this.

KTibow 11 months ago [–]

Probably even worse, since I've heard that it's hard to steer away from the most common interpretation of a question.

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