GPT-5.4 vs GLM-5.2
OpenAI GPT-5.4 | Z.ai GLM-5.2 | |
|---|---|---|
| Overview | ||
| Company | OpenAI | Z.ai |
| Release date | Mar 5 2026 | Jun 16 2026 |
| Access | Proprietary | Open Weight |
| Specifications | ||
Parameters | — | 744B |
Context window | — | 1M |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 48% | — |
Agentic coding SWE-Bench ProCan the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | — | 62.1% |
Agentic terminal coding Terminal-Bench 2.1Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | — | 81% |
Agentic terminal coding Terminal-Bench 2.0Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | 75.1% | — |
Software engineering Expert-SWE (Internal)OpenAI's private set of expert-level software-engineering problems. Higher is better. | 68.5% | — |
General tool use ToolathlonTests how well the AI uses everyday real-world tools and apps to get things done. Higher is better. | 54.6% | — |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | 82.7% | — |
Cybersecurity CyberGymTests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | 79% | — |
Multidisciplinary reasoning Humanity's Last Exam · no toolsHumanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | — | 40.5% |
Advanced math FrontierMath · Tier 1–3Very hard, research-level math problems. Tiers 1–3 are the (still extremely difficult) lower tiers. Higher is better. | 47.6% | — |
Advanced math FrontierMath · Tier 4Very hard, research-level math problems. Tier 4 is the hardest — close to what professional research mathematicians tackle. Higher is better. | 27.1% | — |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 92.8%Best | 91.2% |
Agentic computer use OSWorld-VerifiedCan the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 75% | — |
Knowledge work GDPval (win/tie rate)How often the AI's work matches or beats a human expert's on real knowledge-work tasks. Higher is better. | 83% | — |
| Timeline | ||
| Release gap | GPT-5.4 shipped 103 days before GLM-5.2 | |
Which is better: GPT-5.4 or GLM-5.2?
GPT-5.4 leads GLM-5.2 on 1 of the 1 benchmark they both report (GPQA Diamond). GPT-5.4 shipped 103 days before GLM-5.2, so benchmark comparisons should account for the intervening progress.
GPT-5.4 is proprietary, while GLM-5.2 is open weight.
On GPQA Diamond, GPT-5.4 leads at 92.8% vs GLM-5.2 at 91.2%.
Frequently asked questions
GPT-5.4 was released by OpenAI on Mar 5 2026.
GLM-5.2 was released by Z.ai on Jun 16 2026.
GPT-5.4 leads on GPQA Diamond — GPT-5.4 92.8% vs GLM-5.2 91.2%.
GPT-5.4 is a proprietary model released by OpenAI. GLM-5.2 is an open weight model released by Z.ai.