Unverified50% confidenceBenchmarkExact time
GLM-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17.69
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/26/2026
First Seen
Valid until: 11/24/2026
Sources
Related Entities
Related Claims
UnverifiedGLM 5.2在Artificial Analysis Intelligence Index上，MAX版本得分51分，是目前得分最高的开源权重模型79% similarUnverifiedGLM-5.3的智能体编程准确率随投入词元增加而提升：低投入约24.7，高投入31.5，最大投入34.779% similarUnverifiedGLM 5.2的Diff测试分数从GLM 5.1的18分跃升至46.2分77% similarUnverifiedGLM4在World of AI基准测试工具中排名第五76% similarUnverifiedGLM-5在SWE-Bench Verified基准测试中得分77.8%，位于开源第一梯队75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/802193API
curl https://kongchang.com/api/v1/knowledge/claims/802193MCP
get_claim(id=802193)