AI 导读
K2 Horizon 375B A23B 宁愿拒绝回答也不猜测。它只尝试了 40% 的 AA-Omniscience 问题，产生 26% 的幻觉率，在我们测得的比率中属于较低水平，准确率为 18%，与其前代基本持平。幻觉率的降低相比 K2 Think V2（71%）是巨大改进，使 AA-Omniscience Index 得分从 -40 提升至 -3
正文
K2 Horizon 375B A23B would rather decline a question than guess. It attempts just 40% of AA-Omniscience questions, producing a 26% hallucination rate that ranks among the lower rates we have measured, with accuracy of 18% essentially unchanged from its predecessor. The reduced hallucination is a huge improvement over K2 Think V2 (71%), taking the AA-Omniscience Index score from -40 to -3
来源：@ArtificialAnlys · x.com