DeepSeek-V4-ProvsGLM-5

DeepSeek-V4-Pro
GLM-5
Specifications
Parameters
744B
Benchmarks
Nonsense detection
BullshitBench v2
14%
28%Best
Coding
SWE-Bench Verified
77.8%
Multilingual coding
SWE-Bench Multilingual
73.3%
Competitive coding
LiveCodeBench
93.5%
Agentic terminal coding
Terminal-Bench 2.0
56.2%
Web browsing
BrowseComp
83.4%Best
75.9%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
50.4%
Science
GPQA Diamond
90.1%Best
86%
Community preference
Arena Elo (Text)
1457
Community preference (code)
Arena Elo (Code)
1446Best
1435
Overview
CompanyDeepSeekZ.ai
Release dateApr 24 2026Feb 12 2026
AccessOpen WeightOpen Weight

Which is better: DeepSeek-V4-Pro or GLM-5?

DeepSeek-V4-Pro leads GLM-5 on 3 of the 4 benchmarks they both report (BullshitBench v2, BrowseComp, GPQA Diamond, Arena Elo (Code)). GLM-5 shipped 71 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On BullshitBench v2, GLM-5 leads at 28% vs DeepSeek-V4-Pro at 14%. On BrowseComp, DeepSeek-V4-Pro leads at 83.4% vs GLM-5 at 75.9%. On GPQA Diamond, DeepSeek-V4-Pro leads at 90.1% vs GLM-5 at 86%. On Arena Elo (Code), DeepSeek-V4-Pro leads at 1446 vs GLM-5 at 1435.

Frequently asked questions

DeepSeek-V4-Pro was released by DeepSeek on Apr 24 2026.

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

DeepSeek-V4-Pro leads on GPQA Diamond — DeepSeek-V4-Pro 90.1% vs GLM-5 86%.

Other comparisons