Iniciar sesión
GLM-5.3 logo

GLM-5.3

Z.ai · Lanzado ago 2026

Ver preciosComparar modelos
Condicional

GLM-5.3 is Z.ai's open-weights coding and cyber-defense model on the GLM-5.2 base, with every gain from post-training. Pricing is published at $1.40 input / $4.40 output per 1M, the same as GLM-5.2, and the weights are now on Hugging Face. It stays conditional because its headline coding and cyber scores come from Z.ai's own evaluations: reach for defensive security and agentic automation, but audit it yourself before standardizing.

¿Es adecuada para ti?

Bueno para

  • Defensive cybersecurity: CyberGym 84.5%, top published result ahead of Mythos 5 (83.8%) and GPT-5.6 Sol (83.6%)
  • Long-horizon coding: DeepSWE v1.1 66.9% (from 46.2%), Terminal-Bench 3.0 28.3 (six-fold over 4.6)
  • Agentic automation: AutomationBench v1.0.6 jumps 26.2 to 48.2 (+84%); SAO reinforcement learning drives the long-horizon gains
  • Cost-sensitive frontier-adjacent coding: re-verified on Z.ai's official table at $1.40 input / $4.40 output per 1M, the same standing rate as GLM-5.2 and GLM-5.1 despite the post-training gains
  • Self-hosters: the open weights are now published on Hugging Face (zai-org/GLM-5.3, about 756 GB of safetensors) on the same GLM-5.2 base

No recomendado para

  • Deep offensive exploitation: ExploitBench 54.4% still trails Mythos 5 (78.0%) and GPT-5.6 Sol (76.5%)
  • Budgeting the Flash tier off the launch discount: the 50% promo is no longer on Z.ai's pricing table, which lists GLM-5.3-Flash at $0.15 input / $0.50 output per 1M
  • Modest self-hosting hardware: the published checkpoint is roughly 756 GB, a multi-GPU node deployment rather than a workstation one
  • Vision and multimodal workloads: no multimodal capability announced or benchmarked for GLM-5.3; Z.ai's vision line is a separate GLM-4.6V family
  • Buyers who need independently reproduced results: every headline benchmark remains vendor-run

Rendimiento por tarea

Defensive security (CyberGym)

Excellent

84.5% en CyberGym: el mejor resultado publicado, por delante de la frontera cerrada; reportado por el proveedor, no auditado de forma independiente

Long-horizon software engineering (DeepSWE v1.1)

Very Good

66.9% en DeepSWE v1.1, frente al 46.2%: un salto de 20 puntos, aunque la cifra la ejecutó Z.ai

Terminal/CLI coding (Terminal-Bench 3.0)

Very Good

28.3 en Terminal-Bench 3.0, seis veces más que el 4.6 de GLM-5.2; a la par de la frontera en Terminal-Bench 2.1 (88.2 frente a 88.8)

Deep exploitation (ExploitBench)

Fair

El 54.4% en ExploitBench más que duplica a GLM-5.2 (24.4%), pero aún va 20+ puntos por detrás de la frontera cerrada

Vision / multimodal

Poor

No se anunció ni se midió ninguna capacidad de visión en el lanzamiento

Precios

Entrada

$1.40 / 1M tokens

Salida

$4.40 / 1M tokens

Contexto

1M ctx; Flash $0.15/$0.50, launch promo ended

Ver precios completos

Pruebas de rendimiento

PruebaPuntuaciónFuente
CyberGym84.5% Fuente
DeepSWE v1.166.9% Fuente
Terminal-Bench 3.028.3 Fuente
Terminal-Bench 2.188.2 Fuente
ExploitBench54.4% Fuente
ExploitGym (2h / 6h tasks)105 / 130 Fuente

Historial de veredictos

14 sept 2026
conditional -> conditional (summary corrected): Rating unchanged: the headline coding and cyber benchmarks are still run by Z.ai's own team. The standing summary is corrected: it said per-token pricing was unpublished when Z.ai's table lists $1.40/$4.40, and the entity had stored the expired GLM-5.3-Flash launch promotion as if it were the list rate.

Fuentes

Registro de verificación

  • Precios· Sin cambios

    Agente automatizado

  • Precios· Sin cambios

    Agente automatizado

  • Precios· Sin cambios

    Agente automatizado

  • Precios· Sin cambios

    Agente automatizado

Cómo evaluamos