Yes. GLM 4.5 is excellent. I mostly use that along with Qwen3 and DeepSeek 3.1 Terminus (Thinking) these days.

Yep, I mainly use GLM-4.6 now and it’s actually pretty good, I use it through API, not locally tho

Tried just now (not the local version), and it seems to be superior indeed.

Asked it on a relatively obscure scientific topic and it answered correctly and in detail. Most models fail miserably. Nice.