In plain words: A free-to-use language model that uses only a slice of its 355 billion parts and can think step by step or answer directly, for tool use, reasoning, and coding. It ranked third overall and second on tool-use tasks, with far fewer parts than rivals.
Abstract · GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
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.
GLM-4. 5 Team, :, Aohan Zeng, Xin Lv, Qinkai Zheng, Zhenyu Hou, Bin Chen, Chengxing Xie, Cunxiang Wang, Da Yin, Hao Zeng, Jiajie Zhang, et al.
arXiv:2508.06471 · cs.CL · submitted Aug 8, 2025
abstract · pdf · html
The post-training methodology (Sec 3) is what really stands out to me. The idea of creating specialized 'expert models' for reasoning, agents, and chat, and then distilling their capabilities into a final unified model is a fascinating approach. It feels like a more structured way to solve the "jack of all trades, master of none" problem that can plague generalist models. Instead of just mixing all the data, they're essentially having a generalist learn from a committee of specialists.
A couple of the findings from their RL experiments are pure gold for anyone working in this space. The counter-intuitive result that a single-stage RL process at the full 64K context length outperforms a progressive, multi-stage approach (Fig 6) is a fantastic lesson. I've seen teams assume the opposite would be true. Also, the pragmatic choice to use an XML-like template for function calls to avoid JSON escaping hell (Fig 4) may be a small but brilliant engineering decision that makes a huge difference in practice. Wrangling escaped code inside JSON turns out to be a mess.
The performance on SWE-bench is impressive, putting it in the same league as much larger or proprietary models. What I’d love to see, and maybe others here have thoughts, is whether this hybrid training recipe holds up outside ARC-style evals. For example, do the agentic improvements transfer to messier, real-world workflows where APIs are undocumented, partial failures are common, and user input is full of ambiguity?