GPT-5.4-ProvsGLM-5

GPT-5.4-Pro
GLM-5
Specifications
Parameters
744B
Benchmarks
Nonsense detection
BullshitBench v2
28%
Coding
SWE-Bench Verified
77.8%
Multilingual coding
SWE-Bench Multilingual
73.3%
Agentic terminal coding
Terminal-Bench 2.0
56.2%
Web browsing
BrowseComp
89.3%Best
75.9%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
58.7%Best
50.4%
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%Best
86%
Knowledge work
GDPval (win/tie rate)
82%
Community preference (code)
Arena Elo (Code)
1435
Overview
CompanyOpenAIZ.ai
Release dateMar 5 2026Feb 12 2026
AccessProprietaryOpen Weight

Which is better: GPT-5.4-Pro or GLM-5?

GPT-5.4-Pro leads GLM-5 on 3 of the 3 benchmarks they both report (BrowseComp, Humanity's Last Exam, GPQA Diamond). GLM-5 shipped 21 days before GPT-5.4-Pro, so benchmark comparisons should account for the intervening progress.

GPT-5.4-Pro is proprietary, while GLM-5 is open weight.

On BrowseComp, GPT-5.4-Pro leads at 89.3% vs GLM-5 at 75.9%. On Humanity's Last Exam · with tools, GPT-5.4-Pro leads at 58.7% vs GLM-5 at 50.4%. On GPQA Diamond, GPT-5.4-Pro leads at 94.4% vs GLM-5 at 86%.

Frequently asked questions

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

GLM-5 was released by Z.ai on Feb 12 2026.

GPT-5.4-Pro leads on Humanity's Last Exam · with tools — GPT-5.4-Pro 58.7% vs GLM-5 50.4%.

GPT-5.4-Pro is a proprietary model released by OpenAI. GLM-5 is an open weight model released by Z.ai.

Other comparisons