Neura Intelligence Index

AI Model Benchmarks

Back to Leaderboard

GLM-5.2 vs MiMo-V2-Pro

Z

Zhipu AI 🇨🇳

78.5

#28—

X

Xiaomi 🇨🇳

77.7

#31—

Category Comparison

Benchmark-by-Benchmark

reasoning

Benchmark	GLM-5.2	MiMo-V2-Pro
GPQA Diamond	91.2	—
Humanity's Last Exam	54.7	—

coding

Benchmark	GLM-5.2	MiMo-V2-Pro
SWE-Bench Pro	62.1	—
SWE-bench Verified	—	78

agent

Benchmark	GLM-5.2	MiMo-V2-Pro
Toolathlon	48.2	—
MCP Atlas	76.8	—

Category Winners

coding

X

MiMo-V2-Pro

77.7

reasoning

Z

GLM-5.2

90.2

agent

Z

GLM-5.2

59.6

GLM-5.2 vs MiMo-V2-Pro — Benchmark Comparison | Neura Market