Neura Intelligence Index

AI Model Benchmarks

GLM-4.7 vs Kimi K2.7 Code — Benchmark Comparison | Neura Market

Back to Leaderboard

GLM-4.7 vs Kimi K2.7 Code

Z

Zhipu AI 🇨🇳

66.4

#108—

M

Moonshot AI 🇨🇳

66.8

#105—

Category Comparison

Benchmark-by-Benchmark

reasoning

Benchmark	GLM-4.7	Kimi K2.7 Code
GPQA Diamond	85.7	—
Humanity's Last Exam	42.8	—

math

Benchmark	GLM-4.7	Kimi K2.7 Code
AIME 2025	95.7	—

coding

Benchmark	GLM-4.7	Kimi K2.7 Code
SWE-bench Verified	73.8	—
TerminalBench	33.3	—

agent

Benchmark	GLM-4.7	Kimi K2.7 Code
BrowseComp	52	—
MCP Atlas	—	76

Category Winners

coding

Z

GLM-4.7

56.9

math

Z

GLM-4.7

78.8

reasoning

Z

GLM-4.7

77.0

agent

M

Kimi K2.7 Code

66.8