Saltar al contenido principal

GLM-4.5-Air

Z AIGLMOpen WeightMIT · Uso Comercial

Descripción

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.

Fecha de lanzamiento
2025-07-28
Parámetros
106.0B
Longitud del contexto
131K
Modalidades
text

Radar de capacidades

35
general
60
coding
79
reasoning
45
science
70
agents
0
multimodal

Rankings

Dominio#PosiciónPuntuaciónFuente
Capacidad agéntica85
42.0
LS
Ranking de codificación194
54.0
AA
Ranking general281
45.0
AA
Ciencia283
46.0
AA

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

BFCL-v376.4%Aut.
Terminal-Bench30.0%Aut.
BrowseCompOpenAI (2025)21.3%Aut.

Biology

GPQANYU + Cohere + Anthropic (2023)75.0%Aut.
SciCode37.3%Aut.

Code

LiveCodeBench70.7%Aut.
SWE-Bench Verified57.6%Aut.

Communication

TAU-bench Retail77.9%Aut.
TAU-bench Airline60.8%Aut.

Finance

MMLU-Pro81.4%Aut.

General

AA-Index64.8%Aut.

Math

MATH-50098.1%Aut.
AIME 202489.4%Aut.
Humanity's Last Exam10.6%Aut.

Índices de evaluación AA

(Artificial Analysis)
Math Index(Artificial Analysis)
80.7
Intelligence Index(Artificial Analysis)
16.7
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
1.0
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.8
Aime 25(MAA (Mathematical Association of America))
0.8
Gpqa(NYU + Cohere + Anthropic (2023))
0.7
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.7
Aime(MAA (Mathematical Association of America))
0.7
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.5
Lcr(Artificial Analysis)
0.5
Ifbench(Google Research (2023))
0.4
Scicode(UIUC + Argonne National Lab (2024))
0.3
Terminalbench Hard(Stanford × Laude Institute (2026))
0.2
Hle(Center for AI Safety + Scale AI (2025))
0.1

Puntuaciones por categoría LLM Stats

(LLM Stats (zeroeval))
Language
80
Legal
80
Structured Output
80
Finance
80
Healthcare
80
Communication
70
Tool Calling
70
Math
60
Physics
60
Reasoning
60
Frontend Development
60
General
60
Biology
60
Chemistry
60
Code
50
Agents
40
Search
20
Vision
10

Precios

Precio de entrada$0.17 / 1M tokens
Precio de salida$0.98 / 1M tokens
Precio mixto (3:1)$0.372 / 1M tokens
Precio de lectura caché$0.03 / 1M tokens
Precio de escritura cachéGratis

Velocidad

Tokens/seg0.0
Retraso del primer token0.00s
Tiempo hasta la respuesta0.00s

Ranking de Precios por Proveedor

Ranking de Precios por Proveedor

9 proveedores

Más barato: ZenMuxMás caro: OrcaRouter
ProveedorEntradaSalida
1ZenMuxMás barato
$0.11
$0.56
2302.AI
$0.1143
$0.286
3OpenRouter
$0.13
$0.85
4Kilo Gateway
$0.13
$0.85
5LLM Gateway
$0.13
$0.85
6Z AIPRINCIPAL
$0.17
$0.98
7Z.AI
$0.2
$1.1
8Zhipu AI
$0.2
$1.1
9OrcaRouter
$0.2
$1.1

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas