Release dates
— GLM-5.3 launched with gains attributed entirely to scaled post-training. ↗ — GLM-5.3 weights were released with FP8 and BF16 checkpoints under the custom GLM-5.3 License. ↗
GLM-5.3
Kept the GLM-5.2 base and improved complex coding, long-horizon tasks, and cyber capability entirely through scaled post-training; FP8 and BF16 weights are now public.
MODEL NUMBER040
- First public date
- 2026-08-14
- Organization
- Z.ai
- Family
- GLM
01
Specifications
Only published specifications are shown.
02
Overview
Why it mattered
GLM-5.3 is a clear case of major agent gains coming from scaled post-training, bringing the flagship GLM-5 specification into the open-weight line.
PreviousGLM-5.2— · 1M ctx
CurrentGLM-5.3744B · 1M ctx
04
Architecture & capabilities
Model capabilities
CodingCybersecurityLong-horizon agent
API features
Adjustable reasoning
05
Release history
GLM-5.3 launched with gains attributed entirely to scaled post-training.
View sourceGLM-5.3 weights were released with FP8 and BF16 checkpoints under the custom GLM-5.3 License.
View source06
Related models
Select a card to view the related model.
07
Sources
Suggest a correction
Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.