#45
GLM 4.5 Air
glm-4.5-air
0.0
Helpfulness
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 78 tok/s
Release Date
July 28th, 2025
Lab
Zhipu AI
Type
Open Source
Context Size
131.1K
Max Output Tokens
16.4K
Cost per 1 million tokens
Free
Model Inputs*
Text
Model Outputs*
Text
Tool Calling*
Enabled
Overall Assistant Score
An average score combining the 5 main categories.
70.00 pts
Rank #45
8th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
GLM-4.5-Air is Zhipu AI's lightweight 100B-parameter model designed for efficient local deployment on single H200 GPUs. Achieving SWE-bench 57.6% and GPQA 75.2%, it offers solid performance for cost-conscious teams. With 131K context and 16K output limits, it's available on a free tier plus affordable paid plans. Best for developers prioritizing accessibility and local deployment over maximum capability.

Intelligence

Overall Score; Higher is better

GPT 4o
GLM 4.6
Llama 4 Sco…
Gemini 2.0 …
DeepSeek V3
Gemini 2.5 …
GLM 4.5 Air
Gemini 2.0 …
GLM 4.7 Fla…
Llama 3.3 8…

Speed

Output Tokens per Second; Higher is better

ChatGPT 4o
GPT 4o
Grok 3 Mini
GPT 5.1
Grok 4.1 Fa…
GLM 4.5 Air
GPT 5.2
GLM 5
GPT 5
Gemini 3 Fl…

Price

USD per 1M Tokens; Lower is better

GLM 4.5 Air
GPT-5 Nano
Llama 3.3 8…
DeepSeek V3…
DeepSeek V3…
DeepSeek V3…
GLM 4.7 Fla…
Gemini 2.0 …
Gemini 2.0 …
Gemini 2.5 …

Zhipu AI Models

Overall Score; Same provider comparison

GLM 5
GLM 4.7
GLM 4.6
GLM 4.5 Air
GLM 4.7 Fla…

Zhipu AI Family

Overall Score; Same model family comparison

GLM 5
GLM 4.7
GLM 4.6
GLM 4.5 Air
GLM 4.7 Fla…

Closest Rivals

Overall Score; Nearest by overall rank

GPT 4o
GLM 4.6
Llama 4 Sco…
Gemini 2.0 …
DeepSeek V3
Gemini 2.5 …
GLM 4.5 Air
Gemini 2.0 …
GLM 4.7 Fla…
Llama 3.3 8…