By any chance did you tried Deepseek 4 or 4.1 and GLM 5.3 or flash?
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.
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.