GLM-4.5-Air
Z AIGLMOpen WeightMIT · Commercial OK
描述
GLM-4.5-Air is a more compact variant of GLM-4.5 designed for efficient Agentic, Reasoning, and Coding (ARC) applications. It features 106 billion total parameters with 12 billion active parameters using MoE architecture. Like GLM-4.5, it is a hybrid reasoning model providing thinking mode for complex reasoning and tool usage, and non-thinking mode for immediate responses. Despite its compact design, GLM-4.5-Air delivers competitive performance with a score of 59.8 across 12 industry-standard benchmarks, ranking 6th overall while maintaining superior efficiency. It supports 128K context length and is released under MIT open-source license allowing commercial use.
發布日期
2025-07-28
參數規模
106.0B
上下文長度
131K
支援模態
text
能力雷達圖
38
general
40
coding
79
reasoning
45
science估算
70
agents
0
multimodal
Science 在缺少專門科學評測時使用推理能力代理估算。
排行榜排名
基準測試分數 (LLM Stats)
Agents
BFCL-v3
76.4%自報
Terminal-Bench
30.0%自報
BrowseComp
21.3%自報
Biology
GPQA
75.0%自報
SciCode
37.3%自報
Code
LiveCodeBench
70.7%自報
SWE-Bench Verified
57.6%自報
Communication
TAU-bench Retail
77.9%自報
TAU-bench Airline
60.8%自報
Finance
MMLU-Pro
81.4%自報
General
AA-Index
64.8%自報
Math
MATH-500
98.1%自報
AIME 2024
89.4%自報
Humanity's Last Exam
10.6%自報
AA 評測指數
Math Index80.7
Coding Index23.8
Intelligence Index23.2
Math 5001.0
Mmlu Pro0.8
Aime 250.8
Gpqa0.7
Livecodebench0.7
Aime0.7
Tau20.5
Lcr0.4
Ifbench0.4
Scicode0.3
Terminalbench Hard0.2
Hle0.1
LLM Stats 分類評分
Structured Output80
Finance80
Healthcare80
Language80
Legal80
Tool Calling70
Communication70
General70
Biology60
Chemistry60
Frontend Development60
Math60
Physics60
Reasoning60
Code50
Agents40
Search20
Vision10
定價
輸入價格$0.17 / 1M tokens
輸出價格$0.98 / 1M tokens
混合價格(3:1)$0.372 / 1M tokens
速度
Tokens/秒84.4 tokens/s
首Token延遲1.39s
首回答延遲25.10s
可用提供商
(LS 內部計價單位)暫無提供商資料