Shouldn't it be necessary to run the tests multiple times on each model, since t... | Hacker News

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

csbrooks 3 months ago | parent | context | favorite | on: DeepSeek V4 Pro beats GPT-5.5 Pro on precision

Shouldn't it be necessary to run the tests multiple times on each model, since the results aren't deterministic?

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