Artificial Analysis· @ArtificialAnlys · X·· 2 小时前AI 评分48
AI 导读
HLE-Diamond 分数随 effort 设置提高而显著上升，但成本也随之增加。Claude Opus 5.5 从低 effort（42%）到最高（68%）提升 26 分，每任务成本约为 35 倍；GPT-6 Astra 从低（45%）到最高（64%）提升 19 分，每任务成本为 11 倍。
正文
HLE-Diamond scores increase significantly with higher effort settings, but so does cost. Claude Opus 5.5 gains 26 points from low effort (42%) to max (68%) at ~35x the cost per task, and GPT-6 Astra gains 19 points from low (45%) to max (64%) at 11x the cost per task.
来源：Artificial Analysis · x.com