I've done GLM 5.3 previously here: https://news.ycombinator.com/item?id=49295420

Worth noting though that GLM 5.3 isn't multi-modal, so it doesn't have a vision layer. It is quite clever and hacks around it pretty effectively however. I'm running a deepseek 4 build now and will reply shortly with that.

Awesome. You have a really neat benchmark.

glm5.3-flash is multimodal and I\ve been testing it against opus over the last ~10 days and it does very well at a fraction of the opus price...