Unverified50% confidenceBenchmarkExact time
GLM 5.2在深层Bug实战测试中拿到96分，能识别嵌套三层以上的深层Bug
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/8/2026
First Seen
Valid until: 10/6/2026
Sources
GLM 5.2深度解析：开源编码模型跻身全球前三
bilibili硅基研究所所长6/16/2026
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70% similarUnverifiedGLM4在World of AI基准测试工具中排名第五69% similarUnverifiedGLM-4.7在代码能力基准测试中超过DeepSeek V3.2及Claude Sonnet 4.566% 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66% similarUnverifiedGLM4在SWE-Bench基准测试中得分46.2%，显著优于上一代模型66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/213009API
curl https://kongchang.com/api/v1/knowledge/claims/213009MCP
get_claim(id=213009)