Neura Intelligence Index

AI Model Benchmarks

GLM-4.6 vs MiMo-V2.5-Pro — Benchmark Comparison | Neura Market

Back to Leaderboard

GLM-4.6 vs MiMo-V2.5-Pro

Z

Zhipu AI 🇨🇳

57.5

#146—

X

Xiaomi 🇨🇳

58.2

#143—

Category Comparison

Benchmark-by-Benchmark

reasoning

Benchmark	GLM-4.6	MiMo-V2.5-Pro
GPQA Diamond	81	66.7
Humanity's Last Exam	17.2	34

math

Benchmark	GLM-4.6	MiMo-V2.5-Pro
AIME 2025	93.9	—

coding

Benchmark	GLM-4.6	MiMo-V2.5-Pro
SWE-bench Verified	68	78.9
TerminalBench	40.5	—
SWE-Bench Pro	—	57.2

agent

Benchmark	GLM-4.6	MiMo-V2.5-Pro
BrowseComp	45.1	—

Category Winners

coding

X

MiMo-V2.5-Pro

65.1

math

Z

GLM-4.6

76.1

reasoning

X

MiMo-V2.5-Pro

51.2

agent

Z

GLM-4.6

16.7