GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

TL;DR

GLM-4.5 is a large, open-source Mixture-of-Experts language model with hybrid reasoning capabilities, achieving high performance on reasoning, agentic, and coding benchmarks with fewer parameters than competitors.

Contribution

Introduction of GLM-4.5, a 355B parameter MoE model with hybrid reasoning, trained on 23T tokens, and released alongside a smaller version to advance agentic AI research.

Findings

Achieves 70.1% on TAU-Bench

Scores 91.0% on AIME 24

Releases both large and compact models

Abstract

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.