GLM-4.5-Air vs GLM-5.2
Z.ai GLM-4.5-Air | Z.ai GLM-5.2 | |
|---|---|---|
| Overview | ||
| Company | Z.ai | Z.ai |
| Release date | Jul 28 2025 | Jun 16 2026 |
| Access | Open Weight | Open Weight |
| Specifications | ||
Parameters | 106B | 744B |
Context window | — | 1M |
| Benchmarks | ||
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% |
Coding SWE-Bench VerifiedReal coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 59.8% | — |
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% |
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% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 91.2% |
| Timeline | ||
| Release gap | GLM-4.5-Air shipped 323 days before GLM-5.2 | |
Which is better: GLM-4.5-Air or GLM-5.2?
GLM-4.5-Air and GLM-5.2 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GLM-4.5-Air shipped 323 days before GLM-5.2, so benchmark comparisons should account for the intervening progress.
GLM-4.5-Air has 106B parameters, while GLM-5.2 has 744B.
Direct benchmark comparisons are unavailable — GLM-4.5-Air and GLM-5.2 don't publish scores on any of the same benchmarks.
Frequently asked questions
GLM-4.5-Air was released by Z.ai on Jul 28 2025.
GLM-5.2 was released by Z.ai on Jun 16 2026.
Other comparisons
GLM-4.5-Air vs Claude Fable 5GLM-5.2 vs Claude Fable 5GLM-4.5-Air vs GPT-5.6 SolGLM-5.2 vs GPT-5.6 SolGLM-4.5-Air vs Gemini OmniGLM-5.2 vs Gemini OmniGLM-4.5-Air vs Muse SparkGLM-5.2 vs Muse SparkGLM-4.5-Air vs Grok 4.3 BetaGLM-5.2 vs Grok 4.3 BetaGLM-4.5-Air vs DeepSeek-V4-ProGLM-5.2 vs DeepSeek-V4-Pro