Z.ai
Z.ai: GLM 5.1
z-ai/glm-5.1
GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on a single task for more than 8 hours, autonomously planning, executing, and improving itself throughout the process, ultimately delivering complete, engineering-grade results.
/ 1M tokens
/ 1M tokens
tokens
Limits
Context
204,800
tokens
Max output
128,000
63% of the context window
Parameters
753,864,139,008
Model facts
Author
Z.ai
Tokenizer
Other
Modality
Text -> Text
License
MIT
Created
Apr 7, 2026
Hugging Face
zai-org/GLM-5.1
Default generation parameters
temperature
1
top_p
0.95
Publication status
Modalities
Generation controls
Capability scores
Better than 58% of models compared
Better than 58% of models compared
Better than 65% of models compared
Creative tasks
Category performance
1366 Elo
67.0% win
1336 Elo
62.6% win
1217 Elo
55.5% win
1266 Elo
55.2% win
1290 Elo
55.1% win
1292 Elo
54.9% win
1269 Elo
53.0% win
1145 Elo
44.9% win
Agent tasks
Category performance
1245 Elo
54.4% win
1258 Elo
54.2% win
1241 Elo
53.5% win
1240 Elo
53.3% win
1167 Elo
53.2% win
1205 Elo
52.0% win
Additional published result
Agentic slides (HTML)
1204 Elo · Rank #5 · 51.8% win · Top 54%
1194 Elo
52.0% win
1166 Elo
50.7% win
1158 Elo
50.6% win
1165 Elo
49.8% win
1170 Elo
48.8% win
1053 Elo
37.8% win