#60
GLM 4.6
glm-4.6Helpfulness
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 70 tok/s
Release Date
October 4th, 2025
Lab
Zhipu AI
Type
Open Source
Context Size
200K
Max Output Tokens
131.1K
Cost per 1 million tokens
$0.55 / $2.00
Model Inputs*
Text, Images
Model Outputs*
Text
Tool Calling*
Enabled
Overall Assistant Score
An average score combining the 5 main categories.
75.20 pts
Rank #60
13th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
GLM-4.6 is Zhipu AI's 44B-parameter dense model balancing capability and efficiency. Achieving SWE-bench 68.0%, it rivals Claude Sonnet 4.5 across reasoning and coding. With 200K context and 131K output limits, it offers strong instruction-following (80) and comprehension (78) at $0.55/$2.00 per million tokens. Ideal for teams needing solid mid-tier performance without premium pricing.
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