Expired85% confidenceFactTime unknown
In a summary quality test, the keyword 'used' appeared 12 times in Sonnet's results but only 2 times in Haiku's, meaning Haiku nearly completely ignored the requirement to describe file usage
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedIn a document question-answering test, Haiku captured the additional layer of command-line arguments in a sub-agent priority question, while Sonnet missed it70% similarUnverified在评估潜在危险的网络技能时,Sonnet 5 表现明显弱于 Opus 4.8 和 Mythos 553% similarUnverified语义搜索和关键词搜索单独使用时约每4个结果漏检1个,两者结合漏检率降到约十分之一53% similarUnverified教程式项目(如 MNIST、Titanic、Iris 分类)在简历上几乎没有加分作用,因为数据已高度清洗、问题定义明确、最优解法已公开53% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/24340API
curl https://kongchang.com/api/v1/knowledge/claims/24340MCP
get_claim(id=24340)