GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Team, Aohan Zeng, Lv, Xin, Qinkai Zheng, Zhenyu Hou, Bin Chen, Chengxing Xie, Cunxiang Wang, Yin, Da, Zeng, Hao, Jiajie Zhang, Kedong Wang, Lucen Zhong, M. Liu, Rui Lü, Cao, Shulin, Xiaohan Zhang, Huang, Xuancheng, Wei, Yao, Yean Cheng · arXiv (Cornell University) · 2025
We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that supports both thinking and direct response modes. Through multi-stage training on 23T tokens and comprehensive post-training with expert model iteration and reinforcement learning, GLM-4.5 achieves strong performance across agentic, reasoning, and coding (ARC) tasks, scoring 70.1% on TAU-Bench, 91.0% on AIME 24, and 64.2% on SWE-bench Verified. With much fewer parameters than several competitors, GLM-4.5 ranks 3rd overall among all evaluated models and 2nd on agentic benchmarks. We release both GLM-4.5 (355B parameters) and a compact version, GLM-4.5-Air (106B parameters), to advance research in reasoning and agentic AI systems. Code, models, and more information are available at https://github.com/zai-org/GLM-4.5.