Live data from Hacker News

I hate benchmarks: Moving a production workflow from GPT to GLM-5.3 Flash

Post reply on HN

Print view View original

1–2 of 2 posts

I hate benchmarks: Moving a production workflow from GPT to GLM-5.3 Flash

#1

Post by ahmedelsama » Thu, Sep 03, 2026, 4:49 PM UTC

I hate benchmarks: Moving a production workflow from GPT to GLM-5.3 Flash
polyform.ai

Re: I hate benchmarks: Moving a production workflow from GPT to GLM-5.3 Flash

#2

Post by ahmedelsama » Thu, Sep 03, 2026, 4:49 PM UTC

GLM 5.3 Flash is crushing benchmarks and is dirt cheap. This interested me so I moved our entire step to it and that was a disastor.

Post reply on HN