Unverified50% confidenceBenchmarkExact time
Hy4在Terminal-Bench测试中得分85.4分
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/5/2026
First Seen
Valid until: 9/19/2026
Sources
Related Entities
Related Claims
Unverified在SWE-Bench Multilingual测试中,HY3得分75.8,略微落后于DeepSeek V4 Pro的76.272% similarUnverifiedHy4在DeepSWE测试中得分64.3分67% similarUnverifiedGLM 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65% similarVerifiedSonnet 5在Terminal Bench 2.1上取得80.4%的成绩,接近Opus 4.864% similarUnverifiedGLM4在World of AI基准测试工具中排名第五63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/860615API
curl https://kongchang.com/api/v1/knowledge/claims/860615MCP
get_claim(id=860615)