Neura Intelligence Index

AI Model Benchmarks

GLM-4.7-Flash vs Qwen3 VL 235B A22B Thinking — Benchmark Comparison | Neura Market

Back to Leaderboard

GLM-4.7-Flash vs Qwen3 VL 235B A22B Thinking

Z

Zhipu AI 🇨🇳

45.4

#172—

Q

Qwen3 VL 235B A22B Thinking

Alibaba Cloud / Qwen Team 🇨🇳

44.7

#175—

Category Comparison

Benchmark-by-Benchmark

reasoning

Benchmark	GLM-4.7-Flash	Qwen3 VL 235B A22B Thinking
GPQA Diamond	75.2	—
Humanity's Last Exam	14.4	13.6

math

Benchmark	GLM-4.7-Flash	Qwen3 VL 235B A22B Thinking
AIME 2025	91.6	89.7

coding

Benchmark	GLM-4.7-Flash	Qwen3 VL 235B A22B Thinking
SWE-bench Verified	59.2	—

agent

Benchmark	GLM-4.7-Flash	Qwen3 VL 235B A22B Thinking
BrowseComp	42.8	—
OSWorld	—	38.1

multimodal

Benchmark	GLM-4.7-Flash	Qwen3 VL 235B A22B Thinking
MMMU-Pro	—	69.3
CharXiv Reasoning	—	66.1
ScreenSpot Pro	—	61.8

general

Benchmark	GLM-4.7-Flash	Qwen3 VL 235B A22B Thinking
SimpleQA	—	44.4

Category Winners

coding

Z

GLM-4.7-Flash

35.8

math

Z

GLM-4.7-Flash

72.4

reasoning

Z

GLM-4.7-Flash

42.4

general

Q

Qwen3 VL 235B A22B Thinking

59.5

multimodal

Q

Qwen3 VL 235B A22B Thinking

45.1

agent

Q

Qwen3 VL 235B A22B Thinking

35.7