Expired60% confidenceFactExact time
GLM4在SWE-Bench基准测试中得分46.2%，显著优于上一代模型
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
GLM4 Open-Source Flagship Tested: Crushes Claude and Other Commercial Models in Frontend Development
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79% similarUnverifiedGLM 5.2的Diff测试分数从GLM 5.1的18分跃升至46.2分74% similarUnverifiedGLM 5.2在Frontier SW基准测试中得分为74.4%，接近Anthropic Opus 4.8的水平74% similarUnverifiedGLM4在World of AI基准测试工具中排名第五73% 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17.6973% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/40541API
curl https://kongchang.com/api/v1/knowledge/claims/40541MCP
get_claim(id=40541)