Artificial Analysis· @ArtificialAnlys · X·· 3 小时前AI 评分54
AI 导读
Artificial Analysis 将 GPT-6 Sol（Daybreak Blue, max）以受限访问（trusted-access）模型身份纳入其 Cyber Index，该模型位列 Index 第一。与公开可用的 GPT-6 Sol 相比，Daybreak Blue 版本在 CyberGym-E2E 上提升最大，而该基准正是其观察到安全拒答最多的评测。
正文
GPT-6 Sol (Daybreak Blue, max) has been added to the Artificial Analysis Cyber Index as a trusted-access model, achieving the #1 spot on the Index. Compared to the publicly available GPT-6 Sol, the Daybreak Blue model has the largest gains on CyberGym-E2E, which is the benchmark where we observe the most safety refusals
来源：Artificial Analysis · x.com