Seems like benchmaxing? For example for Terminal-Bench 4 it doesn't have great r... | Hacker News

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

mydreamof 16 days ago | parent | context | favorite | on: Cognition launches new SWE-2 model, Rivaling Fable...

Seems like benchmaxing? For example for Terminal-Bench 4 it doesn't have great results. And why not show other benchmarks?

harmonic18374 16 days ago [–]

Probably, FrontierCode is made by Cognition itself. The model also seems worse in every way than DeepSeek v4.1 Flash, launched today.

Also the submitter's account is very new which makes me suspicious of self-promotion.

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