Unverified50% confidenceFactExact time
GLM 5.2在Terminal Bench测试中得分81分，GLM 5.1得分63.5分，GPT 5.5得分84分，Opus 4.8得分85分
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
GLM 5.2与Zcode实测：每天500万Token免费AI编程工具深度体验
bilibiliNixAI6/18/2026
Related Claims
UnverifiedGLM 5.2的Diff测试分数从GLM 5.1的18分跃升至46.2分83% similarUnverifiedGLM 5.2在Post Train Bench测试中得分34.3分，领先GPT的28.4分，但落后于Opus的37.2分80% similarUnverified测试中GLM 5.1综合得分89.3分，排名第一，超过Claude Sonnet 4.6的87.2分79% similarUnverifiedGLM-5在SWE-Bench Verified基准测试中得分77.8%，位于开源第一梯队78% 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75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/43919API
curl https://kongchang.com/api/v1/knowledge/claims/43919MCP
get_claim(id=43919)