Unverified50% confidenceBenchmarkExact time
GLM-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34.7
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-5.3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17.6979% similarUnverifiedGLM 5.2 scored 51 points on the Artificial Analysis Intelligence Index in its MAX version, making it the highest-scoring open-weight model currently available.68% similarUnverifiedGLM 5.2's Diff test score jumped from 18 points in GLM 5.1 to 46.2 points.68% similarUnverifiedGLM4 scored 74.4% in code reasoning and general knowledge tests, ranking second only to Claude 3 Opus.67% similarUnverifiedGLM4's intelligence level is capable of rivaling mainstream commercial closed-source large models such as Claude 3.5 Sonnet, at a lower usage cost.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/802194API
curl https://kongchang.com/api/v1/knowledge/claims/802194MCP
get_claim(id=802194)