Z.ai
Z.ai: GLM 5V Turbo
z-ai/glm-5v-turbo
GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding, and task execution, and works seamlessly with agents to complete the full loop of “perceive → plan → execute“.
/ 1M tokens
/ 1M tokens
tokens
Limits
Context
202,752
tokens
Max output
131,072
65% of the context window
Model facts
Author
Z.ai
Tokenizer
Other
Modality
Text + Image + Video -> Text
Created
Apr 1, 2026
Default generation parameters
temperature
1
top_p
0.95
Publication status
Modalities
Generation controls
Capability scores
Better than 57% of models compared
Agent tasks
Category performance
1267 Elo
54.8% win
1183 Elo
53.9% win
1164 Elo
52.1% win
1149 Elo
52.0% win
1165 Elo
51.9% win
1171 Elo
51.6% win
1132 Elo
50.4% win
1116 Elo
44.7% win
1120 Elo
44.6% win
1102 Elo
42.5% win
1134 Elo
41.7% win
Additional published result
Agentic slides (HTML)
1137 Elo · Rank #7 · 41.8% win · Top 74%
957 Elo
26.9% win
Creative tasks
Category performance
1209 Elo
52.3% win
1220 Elo
50.0% win
1229 Elo
49.6% win
1231 Elo
48.9% win
1150 Elo
48.8% win
1212 Elo
48.2% win
1202 Elo
47.6% win
1120 Elo
42.8% win