Unverified60% confidenceFactTime unknown

GLM-4.7是一款MOE（混合专家）架构模型，总参数量达358B（3580亿）

2

Sources

60%

Confidence

Long-term

Relevance

6/1/2026

First Seen

Sources

GLM-4.7深度实测：编程能力全面对标Claude Sonnet 4.5

bilibiliAI超元域

Related Entities

GLM-4.7model MOEconcept

Related Claims

Unverified智谱GLM系列从GLM4.5到4.7在358B参数规模上连续打磨三代，随后GLM5翻倍至754B78% similar UnverifiedGLM-5.3在Agents' Last Exam基准上达到开源模型SOTA成绩70% similar UnverifiedGLM-5.3在六项评测中的成绩为：终端编程基准3.0得28.3、深度软件工程基准得66.9、智能体中场考试得28.5、自动化基准得48.2、带工具的人类终极考试得62.5、GDP价值评估AA2版得17.6969% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/24226

API

curl https://kongchang.com/api/v1/knowledge/claims/24226

MCP

get_claim(id=24226)