Qwen3.7-MaxvsGLM-5

Qwen3.7-Max
GLM-5
Specifications
Parameters
744B
Benchmarks
Nonsense detection
BullshitBench v2
28%
Agentic coding
SWE-Bench Pro
60.6%
Coding
SWE-Bench Verified
77.8%
Multilingual coding
SWE-Bench Multilingual
73.3%
Agentic terminal coding
Terminal-Bench 2.0
69.7%Best
56.2%
Multi-step tool use
MCP Atlas
76.4%
Web browsing
BrowseComp
75.9%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
50.4%
Science
GPQA Diamond
92.4%Best
86%
Community preference (code)
Arena Elo (Code)
1435
Overview
CompanyQwenZ.ai
Release dateMay 20 2026Feb 12 2026
AccessProprietaryOpen Weight

Which is better: Qwen3.7-Max or GLM-5?

Qwen3.7-Max leads GLM-5 on 2 of the 2 benchmarks they both report (Terminal-Bench 2.0, GPQA Diamond). GLM-5 shipped 97 days before Qwen3.7-Max, so benchmark comparisons should account for the intervening progress.

Qwen3.7-Max is proprietary, while GLM-5 is open weight.

On Terminal-Bench 2.0, Qwen3.7-Max leads at 69.7% vs GLM-5 at 56.2%. On GPQA Diamond, Qwen3.7-Max leads at 92.4% vs GLM-5 at 86%.

Frequently asked questions

Qwen3.7-Max was released by Qwen on May 20 2026.

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

Qwen3.7-Max leads on Terminal-Bench 2.0 — Qwen3.7-Max 69.7% vs GLM-5 56.2%.

Qwen3.7-Max leads on GPQA Diamond — Qwen3.7-Max 92.4% vs GLM-5 86%.

Qwen3.7-Max is a proprietary model released by Qwen. GLM-5 is an open weight model released by Z.ai.

Other comparisons