Neura Intelligence Index

AI Model Benchmarks

DeepSeek-V3.2 vs GLM-4.7 — Benchmark Comparison | Neura Market

Back to Leaderboard

DeepSeek-V3.2 vs GLM-4.7

DeepSeek 🇨🇳

67.0

#114—

Z

Zhipu AI 🇨🇳

66.3

#117—

Category Comparison

Benchmark-by-Benchmark

reasoning

Benchmark	DeepSeek-V3.2	GLM-4.7
GPQA Diamond	82.4	85.7
Humanity's Last Exam	40.8	42.8

math

Benchmark	DeepSeek-V3.2	GLM-4.7
AIME 2025	93.1	95.7

coding

Benchmark	DeepSeek-V3.2	GLM-4.7
SWE-bench Verified	73.1	73.8
TerminalBench	—	33.3

agent

Benchmark	DeepSeek-V3.2	GLM-4.7
BrowseComp	51.4	52
Toolathlon	35.2	—

Category Winners

coding

DeepSeek-V3.2

67.3

math

Z

GLM-4.7

79.0

reasoning

Z

GLM-4.7

77.3

agent

Z

GLM-4.7

23.0