跳到正文
原文
行业Artificial Analysis · X· @ArtificialAnlys·· 4 小时前

4810 次浏览 · 45 赞 · 3 转发 (收录时)

Artificial Analysis 将于明天通过其 API 提供 CritPt v2 评分服务器

谁
Artificial Analysis
引文
We’ve worked with the CritPt authors to finalize the CritPt v2 grading server and will be making this available to the community via Artificial Analysis’ API tomorrow.

发生了什么

Artificial Analysis 表示,已与 CritPt 作者完成 CritPt v2 评分服务器,并将于明天通过其 API 向社区开放。作者对评分逻辑所做的稳健性改进已纳入 Artificial Analysis Intelligence Index v5.0.1;重新评估所有模型后,大多数模型的分数略有上升,前沿模型的排名保持不变,分数变动最多为 1 分。

接下来读什么

查看这件事的完整进展Artificial Analysis 计划发布 CritPt v2 评分服务器 API
正文 · 中文版本尚未就绪(原文)

We’ve worked with the CritPt authors to finalize the CritPt v2 grading server and will be making this available to the community via Artificial Analysis’ API tomorrow. As part of this process the authors made robustness improvements to the grading server logic, which we have incorporated as v5.0.1 of the Artificial Analysis Intelligence Index

We regraded every model and observe small score increases for most models. Intelligence Index rankings are unchanged among frontier models, with scores moving by at most 1 point.

Thanks to @MiniHui_zhu, @MinyangTian1 and the rest of the CritPt team for their ongoing collaboration

这件事到目前为止

Artificial Analysis 表示,已与 CritPt 作者完成 CritPt v2 评分服务器,并计划于明天通过其 API 向社区开放。作者对评分逻辑所做的稳健性改进已纳入 Artificial Analysis Intelligence Index 5.0.1 版。对所有模型重新评分后,Artificial Analysis 报告称,大多数分数略有上升,前沿模型的排名保持不变,分数变化不超过 1 分。

每天一封,跟上 AI 的重要变化

模型发布、价格变化、算力进展,附原始来源。免费,确认后开始发送,随时一键退订。 看一份往期日报 · 2026-11-04