GPT-5.2 · Humanity's Last Exam · 2,500-question benchmark · 成绩与配置

GPT-5.2 的 Humanity's Last Exam · 2,500-question benchmark 记录。本次发布有 4 条成绩记录,含 4 条精确值(可含历史记录),附 1 条来源定位。

成绩与评测条件

GPT-5.2 · Humanity's Last Exam 成绩与配置
指标与成绩配置与评测条件出处
Accuracy34.5%原文 34.5% · 单位 %
公布 未确认
GPT-5.2 Thinking (xhigh)
设置
Highest available API reasoning effort xhigh, except professional benchmark tasks.
未知项
未另记
工具
禁止工具
推理预算
xhigh
框架
未记录
协议
HLE, no tools; exact subset/version not restated in table.
条件
Highest available API reasoning effort xhigh.
在排名中查看此成绩
Accuracy36.6%原文 36.6% · 单位 %
公布 未确认
GPT-5.2 Pro (xhigh)
设置
Pro variant; highest available API reasoning effort xhigh except professional benchmark tasks.
未知项
The article does not publish a Pro GDPval result under the same heavy setting as the Thinking result; reported row retained as printed.
工具
禁止工具
推理预算
xhigh
框架
未记录
协议
HLE, no tools; exact subset/version not restated in table.
条件
GPT-5.2 Pro; highest available API effort xhigh.
在排名中查看此成绩
Accuracy45.5%原文 45.5% · 单位 %
公布 未确认
GPT-5.2 Thinking (xhigh)
设置
Highest available API reasoning effort xhigh, except professional benchmark tasks.
未知项
未另记
工具
允许工具
推理预算
xhigh
框架
未记录
协议
HLE with search and Python; exact subset/version not restated in table.
条件
Highest available API reasoning effort xhigh.
在排名中查看此成绩
Accuracy50%原文 50.0% · 单位 %
公布 未确认
GPT-5.2 Pro (xhigh)
设置
Pro variant; highest available API reasoning effort xhigh except professional benchmark tasks.
未知项
The article does not publish a Pro GDPval result under the same heavy setting as the Thinking result; reported row retained as printed.
工具
允许工具
推理预算
xhigh
框架
未记录
协议
HLE with search and Python; exact subset/version not restated in table.
条件
GPT-5.2 Pro; highest available API effort xhigh.
在排名中查看此成绩

出处与披露

测试版本与指标

别名 HLE、Humanity’s Last Exam、Humanity's Last Exam

  • Accuracy · % · 越高越好