DeepSeek-V4-Flash-0731vsGLM-5.1

DeepSeek-V4-Flash-0731
GLM-5.1
Specifications
Parameters
744B
Context window
200k
Benchmarks
Nonsense detection
BullshitBench v2
38%Best
22%
Next.js coding
Next.js Evals
75%
Agentic terminal coding
Terminal-Bench 2.1
82.7%
Agentic terminal coding
Terminal-Bench 2.0
63.5%
Personal tool use
Toolathlon-Verified
70.3%
Web browsing
BrowseComp
68%
Cybersecurity
CyberGym
76.7%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
52.3%
Science
GPQA Diamond
86.2%
Business workflows
AutomationBench
25.1%
Community preference (code)
Arena Elo (Code)
1518
Overview
CompanyDeepSeekZ.ai
Release dateJul 31 2026Apr 7 2026
AccessProprietaryOpen Weight

Which is better: DeepSeek-V4-Flash-0731 or GLM-5.1?

DeepSeek-V4-Flash-0731 leads GLM-5.1 on 1 of the 1 benchmark they both report (BullshitBench v2). GLM-5.1 shipped 115 days before DeepSeek-V4-Flash-0731, so benchmark comparisons should account for the intervening progress.

DeepSeek-V4-Flash-0731 is proprietary, while GLM-5.1 is open weight.

On BullshitBench v2, DeepSeek-V4-Flash-0731 leads at 38% vs GLM-5.1 at 22%.

Frequently asked questions

DeepSeek-V4-Flash-0731 was released by DeepSeek on Jul 31 2026.

GLM-5.1 was released by Z.ai on Apr 7 2026.

DeepSeek-V4-Flash-0731 is a proprietary model released by DeepSeek. GLM-5.1 is an open weight model released by Z.ai.

Other comparisons