Tbf, most of the "real benchmarks" have issues that are just as bad. Assessing L... | Hacker News

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

wongarsu 18 days ago | parent | context | favorite | on: GLM 5.2 vs. Opus

Tbf, most of the "real benchmarks" have issues that are just as bad. Assessing LLM performance is just hard

oceansky 18 days ago [–]

And personal too. Different engineers are using them for different use cases.

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