Z.ai
Z.ai: GLM 5.3
z-ai/glm-5.3
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency. Reasoning is always on and cannot be disabled. Reasoning efforts `low`, `high`, and `max` are supported; `max` is the default.
/ 1M tokens
/ 1M tokens
tokens
Limits
Context
1,048,576
tokens
Max output
943,718
90% of the context window
Parameters
753,329,940,480
Model facts
Author
Z.ai
Tokenizer
Other
Modality
Text -> Text
License
Other
Created
Aug 18, 2026
Hugging Face
zai-org/GLM-5.3
Default generation parameters
temperature
1
top_p
0.95
Reasoning
Publication status
Modalities
Generation controls
Capability scores
Better than 93% of models compared
Better than 85% of models compared
Better than 90% of models compared
Creative tasks
Category performance
1334 Elo
59.4% win
1293 Elo
56.8% win
1314 Elo
56.8% win
1306 Elo
54.2% win
1297 Elo
54.1% win
1315 Elo
52.7% win
1261 Elo
51.8% win
1213 Elo
47.2% win
Agent tasks
Category performance
1191 Elo
52.2% win
1255 Elo
51.2% win
1189 Elo
39.1% win