#28
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 #28
61th 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.
Overall Score vs Price
Price axis is logarithmic (USD per 1M input tokens) · Higher score and lower price is better
Ringed point is this model
Anthropic
DeepSeek
Google
Meta
Moonshot
OpenAI
SpaceX AI
Zhipu AI
Intelligence
Overall Score · Higher is better
Speed
Output tokens per second · Higher is better
Price
USD per 1M input tokens · Lower is better
Zhipu AI Models
Overall Score · Same provider
GLM Family
Overall Score · Same model family
Closest Rivals
Overall Score · Nearest by overall rank