Saltar al contenido principal

GLM-5.1 (Reasoning)

Z AIGLMOpen WeightMIT · Commercial OK

Descripción

GLM-5.1 is Z.AI's next-generation flagship foundation model designed for long-horizon agentic engineering tasks. Built on a 754B MoE architecture (40B active parameters), it can work continuously and autonomously on a single task for up to 8 hours, completing the full loop from planning and execution to iterative optimization and delivery. GLM-5.1 achieves state-of-the-art on SWE-Bench Pro (58.4) and demonstrates strong performance across coding, reasoning, and agentic benchmarks. It supports 200K context length, 128K max output tokens, thinking mode, function calling, structured output, context caching, and MCP integration. Overall performance is aligned with Claude Opus 4.6 with particular strengths in sustained execution and complex engineering optimization.

Fecha de lanzamiento
2026-04-07
Parámetros
754.0B
Longitud del contexto
203K
Modalidades
text

Radar de capacidades

46
general
43
coding
87
reasoning
60
scienceest.
60
agents
0
multimodal

Science usa un proxy de razonamiento cuando los benchmarks científicos dedicados no están disponibles.

Rankings

Dominio#PosiciónPuntuaciónFuente
Agents & Tools21
67.0
LS
Code Ranking40
75.0
AA
General Ranking9
90.0
AA
Science33
76.0
AA

Puntuaciones de benchmarks (LLM Stats)

Agents

Vending-Bench 2563441.0%Aut.
BrowseComp79.3%Aut.
MCP Atlas71.8%Aut.
TAU3-Bench70.6%Aut.
Terminal-Bench 2.069.0%Aut.
CyberGym68.7%Aut.
SWE-Bench Pro58.4%Aut.
NL2Repo42.7%Aut.
Toolathlon40.7%Aut.

Biology

GPQA86.2%Aut.

Math

AIME 202695.3%Aut.
HMMT 202594.0%Aut.
IMO-AnswerBench83.8%Aut.
HMMT Feb 2682.6%Aut.
Humanity's Last Exam52.3%Aut.

Índices de evaluación AA

Intelligence Index
51.4
Coding Index
43.4
Tau2
1.0
Gpqa
0.9
Ifbench
0.8
Lcr
0.6
Scicode
0.4
Terminalbench Hard
0.4
Hle
0.3

Puntuaciones por categoría LLM Stats

Agents
100
Reasoning
100
Biology
90
Chemistry
90
General
90
Physics
90
Math
80
Search
80
Code
70
Safety
70
Tool Calling
60
Vision
50
Coding
40

Precios

Precio de entrada$1.4 / 1M tokens
Precio de salida$4.4 / 1M tokens
Precio mixto (3:1)$2.15 / 1M tokens

Velocidad

Tokens/seg53.8 tokens/s
Retraso del primer token1.04s
Tiempo hasta la respuesta71.55s

Proveedores disponibles

(Unidades internas LS)
ProveedorPrecio de entradaPrecio de salida
ZAI1.4M4.4M

Fuentes externas