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.
More from Models
- Opus 5 might be a very deep model or use looping, commentator speculates — scaling01 · 2026-10-16
- GPT-6.1 Sol audit finds 6% of arXiv papers had false main theorems, down to 1.5% recently — nitarshan · 2026-10-16
- Nvidia-backed post-training pushes Nemotron 3.5 VL past frontier on dermatology diagnosis — LoganGrasby · 2026-10-16
- Gemini 4 Argon scores 97.5% on ARC-AGI-3, second lab above 95% — patience_cave · 2026-10-16
- Microsoft MAI claims SOTA 3T-param in-house base models, post-training results coming — soldni · 2026-10-16
- Datadog's Scout 1.0: post-trained GLM-5.3 Flash matches frontier models for AI SRE at lower cost — Tim_Dettmers · 2026-10-16