Qwen3.6vsGLM-5

Qwen3.6
GLM-5
Specifications
Parameters
35B
744B
Context window
256k
Benchmarks
Nonsense detection
BullshitBench v2
28%
Agentic coding
SWE-Bench Pro
49.5%
Coding
SWE-Bench Verified
73.4%
77.8%Best
Multilingual coding
SWE-Bench Multilingual
67.2%
73.3%Best
Agentic terminal coding
Terminal-Bench 2.0
51.5%
56.2%Best
Web browsing
BrowseComp
75.9%
Multidisciplinary reasoning
Humanity's Last Exam · no tools
21.4%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
50.4%
Science
GPQA Diamond
86%
86%
Chart reasoning
CharXiv Reasoning
78%
Multimodal reasoning
MMMU-Pro
75.3%
Multimodal
MMMU
81.7%
Community preference (code)
Arena Elo (Code)
1435
Overview
CompanyQwenZ.ai
Release dateApr 16 2026Feb 12 2026
AccessOpen WeightOpen Weight

Which is better: Qwen3.6 or GLM-5?

GLM-5 leads Qwen3.6 on 3 of the 4 benchmarks they both report (SWE-Bench Verified, SWE-Bench Multilingual, Terminal-Bench 2.0, GPQA Diamond). GLM-5 shipped 63 days before Qwen3.6, so benchmark comparisons should account for the intervening progress.

Qwen3.6 has 35B parameters, while GLM-5 has 744B.

On SWE-Bench Verified, GLM-5 leads at 77.8% vs Qwen3.6 at 73.4%. On SWE-Bench Multilingual, GLM-5 leads at 73.3% vs Qwen3.6 at 67.2%. On Terminal-Bench 2.0, GLM-5 leads at 56.2% vs Qwen3.6 at 51.5%. On GPQA Diamond, both models score 86%.

Frequently asked questions

Qwen3.6 was released by Qwen on Apr 16 2026.

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

GLM-5 leads on SWE-Bench Verified — Qwen3.6 73.4% vs GLM-5 77.8%.

Other comparisons