Artificial Analysis 新指数拉大开源与闭源模型差距
原标题：New Artificial Analysis index widens the gap between open and closed models
AI 摘要
Artificial Analysis 全面改版其 Intelligence Index，将 60% 的评测权重改为私有测试集，以遏制针对公开题库的过拟合训练（benchmaxxing）。改版后 Kimi K3.1 Pro 从第 4 名跌至第 9 名，开源模型与榜首的差距从 3 分扩大到 12 分，Grok 4.7 也下降 12 分。研究者 Nathan Lambert 认为差距还源于强化学习基础设施能力差异；私有测试集的代价是外部无法再发现题目错误，AA-Omniscience 测试中确实存在需修订的模糊或错误题目。
正文节选
New Artificial Analysis index widens the gap between open and closed models Artificial Analysis overhauled its Intelligence Index, causing Kimi K3.1 Pro to drop five spots in the rankings. The model originally launched in fourth place, but it falls to ninth behind eight closed models in version 5. Artificial Analysis now puts the gap between open models and the top of the leaderboard at 12 points, up from 3 points previously. For the first time, 60 percent of the index relies on private test set