DeepSeek-V4-Pro-0813vsGLM-4.7

DeepSeek-V4-Pro-0813
GLM-4.7
Specifications
Context window
128k
Benchmarks
Coding
SWE-Bench Verified
73.8%
Agentic terminal coding
Terminal-Bench 2.1
87.9%
Agentic terminal coding
Terminal-Bench 2.0
41%
Personal tool use
Toolathlon-Verified
74.1%
Web browsing
BrowseComp
52%
Cybersecurity
CyberGym
83.3%
Multidisciplinary reasoning
Humanity's Last Exam · no tools
42.7%Best
24.8%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
60%Best
42.8%
Science
GPQA Diamond
85.7%
Business workflows
AutomationBench
31.8%
Community preference (code)
Arena Elo (Code)
1433
Overview
CompanyDeepSeekZ.ai
Release dateAug 13 2026Dec 22 2025
AccessProprietaryOpen Weight

Which is better: DeepSeek-V4-Pro-0813 or GLM-4.7?

DeepSeek-V4-Pro-0813 leads GLM-4.7 on 2 of the 2 benchmarks they both report (Humanity's Last Exam). GLM-4.7 shipped 234 days before DeepSeek-V4-Pro-0813, so benchmark comparisons should account for the intervening progress.

DeepSeek-V4-Pro-0813 is proprietary, while GLM-4.7 is open weight.

On Humanity's Last Exam · no tools, DeepSeek-V4-Pro-0813 leads at 42.7% vs GLM-4.7 at 24.8%. On Humanity's Last Exam · with tools, DeepSeek-V4-Pro-0813 leads at 60% vs GLM-4.7 at 42.8%.

Frequently asked questions

DeepSeek-V4-Pro-0813 was released by DeepSeek on Aug 13 2026.

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

DeepSeek-V4-Pro-0813 leads on Humanity's Last Exam · no tools — DeepSeek-V4-Pro-0813 42.7% vs GLM-4.7 24.8%.

DeepSeek-V4-Pro-0813 is a proprietary model released by DeepSeek. GLM-4.7 is an open weight model released by Z.ai.

Other comparisons