DeepSeek-V4-Flash-0731vsGLM-4.5

DeepSeek-V4-Flash-0731
GLM-4.5
Specifications
Parameters
355B
Context window
128k
Benchmarks
Nonsense detection
BullshitBench v2
38%Best
8%
Coding
SWE-Bench Verified
64.2%
Agentic terminal coding
Terminal-Bench 2.1
82.7%
Personal tool use
Toolathlon-Verified
70.3%
Cybersecurity
CyberGym
76.7%
Science
GPQA Diamond
79.1%
Business workflows
AutomationBench
25.1%
Overview
CompanyDeepSeekZ.ai
Release dateJul 31 2026Jul 28 2025
AccessProprietaryOpen Weight

Which is better: DeepSeek-V4-Flash-0731 or GLM-4.5?

DeepSeek-V4-Flash-0731 leads GLM-4.5 on 1 of the 1 benchmark they both report (BullshitBench v2). GLM-4.5 shipped 368 days before DeepSeek-V4-Flash-0731, so benchmark comparisons should account for the intervening progress.

DeepSeek-V4-Flash-0731 is proprietary, while GLM-4.5 is open weight.

On BullshitBench v2, DeepSeek-V4-Flash-0731 leads at 38% vs GLM-4.5 at 8%.

Frequently asked questions

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

GLM-4.5 was released by Z.ai on Jul 28 2025.

DeepSeek-V4-Flash-0731 is a proprietary model released by DeepSeek. GLM-4.5 is an open weight model released by Z.ai.

Other comparisons