Zhipu Releases GLM-5.3: Unchanged Base Model, Cybersecurity Boosted by Post-Training

kimmonismus · x · 2026-08-14

Zhipu has launched the GLM-5.3 model. It uses the exact same 743B base model as GLM-5.2, with all improvements attributed entirely to scaling post-training, including more executable environments, longer tasks, and stronger verifiers.

In cybersecurity evaluations, GLM-5.3 shows massive gains: ExploitBench score jumped from 24.4% to 54.4%, and CyberGym score increased from 77.2% to 84.5%. The weights are scheduled for release in two weeks.

Related event: Zhipu AI Releases GLM-5.3 with Boosted Coding and Cybersecurity, Open Weights in Two Weeks(18 posts)→

Original post →

More from Models

Models channel →