I agree. The “frontier level” open weights models benchmark really well but fall... | Hacker News

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

acchow 18 days ago | parent | context | favorite | on: DeepSeek V4 Pro 0813

I agree. The “frontier level” open weights models benchmark really well but fall behind in real world performance

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