Expired60% confidenceFactExact time
GLM4在World of AI基准测试工具中排名第五
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
GLM4开源旗舰实测：前端开发碾压Claude等商业模型
bilibiliAI-seeker6/21/2026
Related Claims
UnverifiedGLM-5在SWE-Bench Verified基准测试中得分77.8%，位于开源第一梯队78% similarUnverifiedGLM-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17.6976% similarUnverifiedGLM-5.3在Agents' Last Exam基准上达到开源模型SOTA成绩73% similarUnverifiedGLM-4.7是一款MOE（混合专家）架构模型，总参数量达358B（3580亿）73% similarUnverifiedGLM4在SWE-Bench基准测试中得分46.2%，显著优于上一代模型73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/40630API
curl https://kongchang.com/api/v1/knowledge/claims/40630MCP
get_claim(id=40630)