GLM-5.2 is the new leading open weights model on Artificial Analysis (artificialanalysis.ai)

Z ai has unveiled GLM-5.2, which now holds the title of the leading open weights model on the Artificial Analysis Intelligence Index, scoring an impressive 51. This new model matches its predecessor GLM-5.1 in size, featuring 744 billion total parameters with 40 billion active parameters, yet it surpasses it by 11 points on the Intelligence Index. GLM-5.2 demonstrates significant improvements, particularly in scientific reasoning, and notably outperforms competing models like MiniMax-M3 and DeepSeek V4 Pro in various benchmarks, including GDPval-AA v2, where it scores 1524. The significance of GLM-5.2 lies not only in its enhanced performance metrics but also in its cost-effectiveness; it's positioned on the Pareto frontier for Intelligence versus Cost per Task, costing approximately $0.46 per task, which, while higher than some models, keeps it competitive given its intelligence level. Furthermore, the model employs 43,000 output tokens per task—higher than many similar models—indicating a trade-off between output efficiency and task performance. With its MIT license and availability across numerous third-party providers, GLM-5.2 is poised to be a pivotal player in real-world AI applications.