On August 11, Zhipu Company announced the official release and open-sourcing of its advanced visual reasoning model, GLM-4.5V. Boasting a total of 106 billion parameters and 12 billion active parameters, GLM-4.5V is now available on the ModelScope community and Hugging Face platform. Building upon Zhipu's groundbreaking GLM-4.5-Air text-based model and adhering to the technological path of GLM-4.1V-Thinking, GLM-4.5V has demonstrated state-of-the-art (SOTA) performance across 41 public visual multimodal benchmarks, positioning it as an ideal solution for various tasks encompassing image and video processing, document understanding, and GUI Agent functionalities.