GLM-5.3 (max) Tops Artificial Analysis Intelligence Index

GLM-5.3 Artificial Analysis Benchmarks

Artificial Analysis has benchmarked GLM-5.3 (max), the latest model from Zhipu AI, using its Intelligence Index v4.1.1, which combines nine evaluations including GDPval-AA v2, Terminal-Bench v2.1, and Humanity's Last Exam. The model leads the index, with a strong balance of intelligence, cost-efficiency, and a large context window. The analysis also breaks down performance by task type, token usage, and pricing, offering a detailed look at how GLM-5.3 (max) compares to other open and proprietary models.