GLM-4.5 - Unifying agentic capabilities in one open model
GLM-4.5 is a new 355B parameter open-weight MoE model (32B active). It delivers state-of-the-art performance on reasoning, code, and agentic tasks. Both the 355B flagship and a 106B Air version are now available, featuring dual-mode inference.
Replies
Strong coding ability, able to generate small games with just one sentence, including full stack code for both front-end and back-end
The agentic capability is very promising. We can build slides and websites very quickly with just a few sentences.
I am amazed by the capabilities of 4.5, and it feels like a significant improvement over the previous generation.
impressive CREATION
Impressive work! Nowdays, best open source model.
GPT-4o
Ngl, making high-perf GLM models free to play with in such a clean UI is just genius—testing new AI stuff has never been this chill, fr.
Great. Even more great that you guys made it open source. It's the future. One question: Is there any way we can integrate it in our own web apps like any other LLMs? If there is, is it compatible with popular wrappers which can be used to use most LLMs out there without using any other wrapper?