Unverified75% confidenceFactTime unknown
GLM-4.7在代码能力基准测试中超过DeepSeek V3.2及Claude Sonnet 4.5
1
Sources
75%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026
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
Related Claims
Unverified国产模型中编程能力最强的GLM 5.1，实测水平大致处于Claude Opus 4.5和Sonnet 4.6之间77% similarUnverifiedGLM 4.6在HumanEval、MBPP、SWE-bench等代码评测基准以及MMLU、GPQA等综合能力基准上的表现对齐Claude 3.4和Claude 3.4.577% similarUnverifiedGLM 5.2 在前端生成质量上优于 Claude Sonnet 575% similarUnverifiedGLM4的智能水平足以媲美Claude 3.5 Sonnet等主流商业闭源大模型，且使用成本更低73% similarUnverified根据Anthropic发布的基准测试数据，Sonnet 4.5在编码能力上略优于Claude Opus 4.172% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/24229API
curl https://kongchang.com/api/v1/knowledge/claims/24229MCP
get_claim(id=24229)