Artificial Analysis· @ArtificialAnlys · X·· 2 小时前AI 评分48
AI 导读
HLE-Diamond 将每道题标注为推理或知识，得分超过 50% 的模型在推理任务上均比知识任务高 16-35 分。GPT-6.1 Sol (max) 在领先者中差距最大，推理得分 76%，知识得分 41%。
正文
HLE-Diamond labels every question as reasoning or knowledge, and the models above 50% all score 16-35 points higher on reasoning tasks than knowledge. GPT-6.1 Sol (max) has the widest gap among the leaders, scoring 76% on reasoning and 41% on knowledge.
来源：Artificial Analysis · x.com