GPT-5.4-ProvsGLM-5.3

GPT-5.4-Pro
GLM-5.3
Specifications
Parameters
743B
Benchmarks
Agentic coding
DeepSWE 1.1
66.9%
Agentic terminal coding
Terminal-Bench 3.0
28.3%
Web browsing
BrowseComp
89.3%
Cybersecurity
CyberGym
84.5%
Cybersecurity
ExploitBench
54.4%
Cybersecurity
ExploitGym · 6-hour budget
130
Cybersecurity
ExploitGym · 2-hour budget
105
Multidisciplinary reasoning
Humanity's Last Exam · with tools
58.7%
62.5%Best
Abstract reasoning
ARC-AGI-2
83.3%
Advanced math
FrontierMath · Tier 1–3
50%
Advanced math
FrontierMath · Tier 4
38%
Science
GPQA Diamond
94.4%
Agentic computer use
Agent's Last Exam
28.5%
Business workflows
AutomationBench
48.2%
Knowledge work
GDPval-AA v2
1769
Knowledge work
GDPval (win/tie rate)
82%
Overview
CompanyOpenAIZ.ai
Release dateMar 5 2026Aug 14 2026
AccessProprietaryProprietary

Which is better: GPT-5.4-Pro or GLM-5.3?

GLM-5.3 leads GPT-5.4-Pro on 1 of the 1 benchmark they both report (Humanity's Last Exam). GPT-5.4-Pro shipped 162 days before GLM-5.3, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On Humanity's Last Exam · with tools, GLM-5.3 leads at 62.5% vs GPT-5.4-Pro at 58.7%.

Frequently asked questions

GPT-5.4-Pro was released by OpenAI on Mar 5 2026.

GLM-5.3 was released by Z.ai on Aug 14 2026.

GLM-5.3 leads on Humanity's Last Exam · with tools — GPT-5.4-Pro 58.7% vs GLM-5.3 62.5%.

Other comparisons