Qwen3.5vsGLM-5

Qwen3.5
GLM-5
Specifications
Parameters
397B
744B
Context window
1M
Benchmarks
Nonsense detection
BullshitBench v2
28%
Coding
SWE-Bench Verified
76.4%
77.8%Best
Multilingual coding
SWE-Bench Multilingual
69.3%
73.3%Best
Agentic terminal coding
Terminal-Bench 2.0
52.5%
56.2%Best
Web browsing
BrowseComp
69%
75.9%Best
Multidisciplinary reasoning
Humanity's Last Exam · no tools
28.7%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
50.4%
Science
GPQA Diamond
88.4%Best
86%
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)
1435
Overview
CompanyQwenZ.ai
Release dateFeb 16 2026Feb 12 2026
AccessOpen WeightOpen Weight

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

GLM-5 leads Qwen3.5 on 4 of the 5 benchmarks they both report. GLM-5 shipped 4 days before Qwen3.5, so benchmark comparisons should account for the intervening progress.

Qwen3.5 has 397B parameters, while GLM-5 has 744B.

On SWE-Bench Verified, GLM-5 leads at 77.8% vs Qwen3.5 at 76.4%. On SWE-Bench Multilingual, GLM-5 leads at 73.3% vs Qwen3.5 at 69.3%. On Terminal-Bench 2.0, GLM-5 leads at 56.2% vs Qwen3.5 at 52.5%. On BrowseComp, GLM-5 leads at 75.9% vs Qwen3.5 at 69%. On GPQA Diamond, Qwen3.5 leads at 88.4% vs GLM-5 at 86%.

Frequently asked questions

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

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

GLM-5 leads on SWE-Bench Verified — Qwen3.5 76.4% vs GLM-5 77.8%.

Qwen3.5 leads on GPQA Diamond — Qwen3.5 88.4% vs GLM-5 86%.

Other comparisons