GPT-5.2 · ARC-AGI-1(Verified set; release article does not specify task count) · 主文证据(ev-gpt52-arc1)

GPT-5.2 的 ARC-AGI-1 · Verified set; release article does not specify task count 官方出处。见《隆重推出 GPT-5.2 | OpenAI》Appendix / Abstract reasoning / ARC-AGI-1 (Verified)。证据 ev-gpt52-arc1。

原文与定位

GPT-5.2 · ARC-AGI-1(Verified set; release article does not specify task count),GPT-5.2 Thinking (xhigh)配置,Accuracy 86.2%(具体成绩公布时间未确认)。见《隆重推出 GPT-5.2 | OpenAI》Appendix / Abstract reasoning / ARC-AGI-1 (Verified)。 查看成绩条件

GPT-5.2 · ARC-AGI-1(Verified set; release article does not specify task count),GPT-5.2 Pro (xhigh)配置,Accuracy 90.5%(具体成绩公布时间未确认)。见《隆重推出 GPT-5.2 | OpenAI》Appendix / Abstract reasoning / ARC-AGI-1 (Verified)。 查看成绩条件

ARC-AGI-1 (Verified): GPT-5.2 Thinking 86.2%; Pro 90.5%.
官方材料
隆重推出 GPT-5.2 | OpenAI
定位
主文 · Appendix / Abstract reasoning / ARC-AGI-1 (Verified)
材料版本
Official release article with full visible benchmark appendix; revision date unknown; Original page date label 2025-12-11; current page revision date is unknown.
版本公布
未确认
披露时间
未确认 · 首发/后补未确认
采集时间
历史依据
暂无可靠历史版本依据
引用文本

GPT-5.2 · ARC-AGI-1(Verified set; release article does not specify task count),GPT-5.2 Thinking (xhigh)配置,Accuracy 86.2%(具体成绩公布时间未确认);GPT-5.2 · ARC-AGI-1(Verified set; release article does not specify task count),GPT-5.2 Pro (xhigh)配置,Accuracy 90.5%(具体成绩公布时间未确认)。官方出处 隆重推出 GPT-5.2 | OpenAI(主文,Official release article with full visible benchmark appendix; revision date unknown; Original page date label 2025-12-11; current page revision date is unknown.)Appendix / Abstract reasoning / ARC-AGI-1 (Verified),https://openai.com/zh-Hans-CN/index/introducing-gpt-5-2/。Benchlog https://benchlog.lekshome.cc/evidence/gpt-5-2/ev-gpt52-arc1/

关联成绩与条件

GPT-5.2 · ARC-AGI-1 成绩与配置
指标与成绩配置与评测条件证据关系
Accuracy86.2%原文 86.2% · 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
工具条件未记录
推理预算
xhigh
框架
未记录
协议
ARC-AGI-1 Verified.
条件
Highest available API reasoning effort xhigh.

直接支持该成绩

在排名中查看此成绩
Accuracy90.5%原文 90.5% · 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
工具条件未记录
推理预算
xhigh
框架
未记录
协议
ARC-AGI-1 Verified.
条件
GPT-5.2 Pro; highest available API effort xhigh.

直接支持该成绩

在排名中查看此成绩