The quality that matters a lot to me is what I call "Helpfulness". An art of being helpful. While GPT came a long way from "you are wrong and I can prove it to you", Claude wins hands down in terms of "being helpful". If task is underspecified or has wrong elements, it will try to correct the best it can.

I read that GLM 5.2 (and other GLM models) were specifically trained to be "helpful" as Claude is. I have big hopes on GLM line of models growing to be a real alternative to the Claude in the near future.