Qwen3.5vsGLM-4.7

Qwen3.5
GLM-4.7
Specifications
Parameters
397B
Context window
1M
128k
Benchmarks
Coding
SWE-Bench Verified
76.4%Best
73.8%
Multilingual coding
SWE-Bench Multilingual
69.3%
Agentic terminal coding
Terminal-Bench 2.0
52.5%Best
41%
Web browsing
BrowseComp
69%Best
52%
Multidisciplinary reasoning
Humanity's Last Exam · no tools
28.7%Best
24.8%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
42.8%
Science
GPQA Diamond
88.4%Best
85.7%
Agentic computer use
OSWorld-Verified
62.2%
Chart reasoning
CharXiv Reasoning
80.8%
Multimodal reasoning
MMMU-Pro
79%
Multimodal
MMMU
85%
Community preference (code)
Arena Elo (Code)
1433
Overview
CompanyQwenZ.ai
Release dateFeb 16 2026Dec 22 2025
AccessOpen WeightOpen Weight

Which is better: Qwen3.5 or GLM-4.7?

Qwen3.5 leads GLM-4.7 on 5 of the 5 benchmarks they both report. GLM-4.7 shipped 56 days before Qwen3.5, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Qwen3.5) vs 128k (GLM-4.7).

On SWE-Bench Verified, Qwen3.5 leads at 76.4% vs GLM-4.7 at 73.8%. On Terminal-Bench 2.0, Qwen3.5 leads at 52.5% vs GLM-4.7 at 41%. On BrowseComp, Qwen3.5 leads at 69% vs GLM-4.7 at 52%. On Humanity's Last Exam · no tools, Qwen3.5 leads at 28.7% vs GLM-4.7 at 24.8%. On GPQA Diamond, Qwen3.5 leads at 88.4% vs GLM-4.7 at 85.7%.

Frequently asked questions

Qwen3.5 was released by Qwen on Feb 16 2026.

GLM-4.7 was released by Z.ai on Dec 22 2025.

Qwen3.5 leads on SWE-Bench Verified — Qwen3.5 76.4% vs GLM-4.7 73.8%.

Qwen3.5 leads on Humanity's Last Exam · no tools — Qwen3.5 28.7% vs GLM-4.7 24.8%.

Qwen3.5 has a 1M context window; GLM-4.7 has 128k.

Other comparisons