Qwen3.8-MaxvsGLM-4.5-Air
Qwen3.8-Max | GLM-4.5-Air | |
|---|---|---|
| Specifications | ||
Parameters | 2.4T | 106B |
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. | 67.7% | — |
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% |
Research reproduction PaperBenchreproducing the results of an ML research paper end to end | 93% | — |
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. | 86.6% | — |
Professional tool use JobBenchTests the AI on professional workplace tasks that require using real work tools — the kind of multi-step jobs an office worker handles. Higher is better. | 53.4% | — |
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. | 86.1% | — |
Chart reasoning CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better. | 88.4% | — |
Visual reasoning BabyVisionTests core visual reasoning — seeing and understanding images the way even young children can, which AIs often find surprisingly hard. Higher is better. | 82% | — |
| Overview | ||
| Company | Qwen | Z.ai |
| Release date | Aug 3 2026 | Jul 28 2025 |
| Access | Proprietary | Open Weight |
Which is better: Qwen3.8-Max or GLM-4.5-Air?
Qwen3.8-Max and GLM-4.5-Air don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GLM-4.5-Air shipped 371 days before Qwen3.8-Max, so benchmark comparisons should account for the intervening progress.
Qwen3.8-Max has 2.4T parameters, while GLM-4.5-Air has 106B. Qwen3.8-Max is proprietary, while GLM-4.5-Air is open weight.
Direct benchmark comparisons are unavailable — Qwen3.8-Max and GLM-4.5-Air don't publish scores on any of the same benchmarks.
Frequently asked questions
Qwen3.8-Max was released by Qwen on Aug 3 2026.
GLM-4.5-Air was released by Z.ai on Jul 28 2025.
Qwen3.8-Max is a proprietary model released by Qwen. GLM-4.5-Air is an open weight model released by Z.ai.
Other comparisons
Qwen3.8-MaxvsClaude Opus 5GLM-4.5-AirvsClaude Opus 5Qwen3.8-MaxvsGPT-5.6 SolGLM-4.5-AirvsGPT-5.6 SolQwen3.8-MaxvsGemini 3.6 FlashGLM-4.5-AirvsGemini 3.6 FlashQwen3.8-MaxvsMuse Spark 1.1GLM-4.5-AirvsMuse Spark 1.1Qwen3.8-MaxvsGrok 4.5GLM-4.5-AirvsGrok 4.5Qwen3.8-MaxvsDeepSeek-V4-Flash-0731GLM-4.5-AirvsDeepSeek-V4-Flash-0731