Zhipu AI's GLM-5.1 Tops SWE-Bench Pro, Outperforming Major AI Rivals

Summary

Zhipu AI (Z.ai), the Chinese AI lab, has reportedly achieved the top score on SWE-Bench Pro — a benchmark designed to evaluate AI models on real-world software engineering tasks — with its GLM-5.1 model. The result positions GLM-5.1 ahead of competing models from major Western and international AI labs, marking a notable milestone for Chinese-developed foundation models in the coding and software engineering domain. SWE-Bench Pro is an evolution of the original SWE-Bench benchmark and tests mod