Qwen3-Coder-NextvsGLM-5

Qwen3-Coder-Next
GLM-5
Specifications
Parameters
80B
744B
Context window
256k
Benchmarks
Nonsense detection
BullshitBench v2
28%
Agentic coding
SWE-Bench Pro
44.3%
Coding
SWE-Bench Verified
70.6%
77.8%Best
Multilingual coding
SWE-Bench Multilingual
62.8%
73.3%Best
Agentic terminal coding
Terminal-Bench 2.0
36.2%
56.2%Best
Web browsing
BrowseComp
75.9%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
50.4%
Science
GPQA Diamond
86%
Community preference (code)
Arena Elo (Code)
1435
Overview
CompanyQwenZ.ai
Release dateFeb 3 2026Feb 12 2026
AccessOpen WeightOpen Weight

Which is better: Qwen3-Coder-Next or GLM-5?

GLM-5 leads Qwen3-Coder-Next on 3 of the 3 benchmarks they both report (SWE-Bench Verified, SWE-Bench Multilingual, Terminal-Bench 2.0). Qwen3-Coder-Next shipped 9 days before GLM-5, so benchmark comparisons should account for the intervening progress.

Qwen3-Coder-Next has 80B parameters, while GLM-5 has 744B.

On SWE-Bench Verified, GLM-5 leads at 77.8% vs Qwen3-Coder-Next at 70.6%. On SWE-Bench Multilingual, GLM-5 leads at 73.3% vs Qwen3-Coder-Next at 62.8%. On Terminal-Bench 2.0, GLM-5 leads at 56.2% vs Qwen3-Coder-Next at 36.2%.

Frequently asked questions

Qwen3-Coder-Next was released by Qwen on Feb 3 2026.

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

GLM-5 leads on SWE-Bench Verified — Qwen3-Coder-Next 70.6% vs GLM-5 77.8%.

Other comparisons