Unverified60% 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
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 5.2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70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/40541API
curl https://kongchang.com/api/v1/knowledge/claims/40541MCP
get_claim(id=40541)