19 August 2026

Zhipu's GLM-5.3 improves without adding more parameters

Zhipu, a Chinese AI lab, released GLM-5.3, an updated version of its large language model that performs better on benchmark tests while keeping the same 753 billion parameters, the numerical weights that define how a model works.
The improvements came from better training methods after the initial model building, specifically using reinforcement learning (training by rewarding desired behaviors) and techniques to compress knowledge from larger systems into smaller ones.
The result suggests AI labs may focus less on simply building larger models and more on refining how they train existing ones to handle complex reasoning tasks.

How it was covered

Zhipu's GLM-5.3 showed major gains on benchmarks while maintaining the same 753B parameter footprint, with improvements attributed to stronger post-training including asynchronous RL and on-policy distillation. This suggests agentic capability scaling is shifting from parameter count toward RL systems and environment quality.