Neura Intelligence Index

AI Model Benchmarks

Back to Leaderboard

GLM-4.7 vs Qwen3-Next-80B-A3B-Thinking

Z

Zhipu AI 🇨🇳

67.0

#86—

Q

Qwen3-Next-80B-A3B-Thinking

Alibaba Cloud / Qwen Team 🇨🇳

66.6

#89—

Category Comparison

Benchmark-by-Benchmark

reasoning

Benchmark	GLM-4.7	Qwen3-Next-80B-A3B-Thinking
GPQA Diamond	85.7	77.2
Humanity's Last Exam	42.8	—

math

Benchmark	GLM-4.7	Qwen3-Next-80B-A3B-Thinking
AIME 2025	95.7	87.8

coding

Benchmark	GLM-4.7	Qwen3-Next-80B-A3B-Thinking
SWE-bench Verified	73.8	—
TerminalBench	33.3	—

agent

Benchmark	GLM-4.7	Qwen3-Next-80B-A3B-Thinking
BrowseComp	52	—
TAU-Bench Retail	—	69.6

Category Winners

coding

Z

GLM-4.7

57.0

math

Z

GLM-4.7

78.5

reasoning

Z

GLM-4.7

78.6

agent

Q

Qwen3-Next-80B-A3B-Thinking

55.5

GLM-4.7 vs Qwen3-Next-80B-A3B-Thinking — Benchmark Comparison | Neura Market