#9
GLM 5
glm-5Helpfulness
Instruction
Following
Comprehension
Empathy
Creative
Writing
Helpfulness
0.0
Instruction Following
0.0
Comprehension
0.0
Empathy
0.0
Creative Writing
0.0
Speed
Avg 72 tok/s
Release Date
February 11, 2026
Lab
Zhipu AI
Type
Open Source
Context Size
200K
Max Output Tokens
128K
Cost per 1 million tokens
$1.00 / $3.20
Model Inputs*
Text, Images
Model Outputs*
Text
Tool Calling*
Enabled
Overall Assistant Score
An average score combining the 5 main categories.
87.54 pts
Rank #9
83th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
GLM-5 is Zhipu AI's flagship 744B parameter Mixture-of-Experts (MoE) model, released on February 11, 2026. It is specifically engineered for "Agentic Engineering," excelling in complex system tasks and long-horizon planning. With a 200k context window and a focus on coding and factual accuracy, it rivals top proprietary models like Claude Opus 4.5 in logic density. While its empathy scores are lower (72.5), its instruction-following (92.5) and creative writing (84.5) capabilities make it a premier choice for open-weight engineering workflows.
Intelligence
Overall Score; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Zhipu AI Models
Overall Score; Same provider comparison
Zhipu AI Family
Overall Score; Same model family comparison
Closest Rivals
Overall Score; Nearest by overall rank