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 · BrowseComp(1,266 题;单代理与多代理按协议区分),GPT-5.2 Thinking (xhigh)配置,Accuracy 65.8%(具体成绩公布时间未确认);GPT-5.2 · BrowseComp(1,266 题;单代理与多代理按协议区分),GPT-5.2 Pro (xhigh)配置,Accuracy 77.9%(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 / Tool use / BrowseComp,https://openai.com/zh-Hans-CN/index/introducing-gpt-5-2/。Benchlog https://benchlog.lekshome.cc/evidence/gpt-5-2/ev-gpt52-browsecomp/
关联成绩与条件
GPT-5.2 · BrowseComp 成绩与配置
指标与成绩
配置与评测条件
证据关系
Accuracy65.8%原文 65.8% · 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
BrowseComp; article notes search blacklisting to reduce answer leakage.
GPT-5.2 · BrowseComp (1,266 题;单代理与多代理按协议区分) · Main text evidence (ev-gpt52-browsecomp)
Official source for BrowseComp · 1,266 题;单代理与多代理按协议区分 in GPT-5.2. See “隆重推出 GPT-5.2 | OpenAI” at Appendix / Tool use / BrowseComp. Evidence ev-gpt52-browsecomp.
Official release article with full visible benchmark appendix; revision date unknown; Original page date label 2025-12-11; current page revision date is unknown.
Version published
Unconfirmed
Disclosure date
Unconfirmed · Launch or later disclosure unconfirmed
Collected
Historical basis
No reliable historical version evidence available
Citation text
GPT-5.2 · BrowseComp (1,266 题;单代理与多代理按协议区分), configuration GPT-5.2 Thinking (xhigh), Accuracy 65.8% (exact score publication date unconfirmed); GPT-5.2 · BrowseComp (1,266 题;单代理与多代理按协议区分), configuration GPT-5.2 Pro (xhigh), Accuracy 77.9% (exact score publication date unconfirmed). Official source: 隆重推出 GPT-5.2 | OpenAI (Main text, 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 / Tool use / BrowseComp, https://openai.com/zh-Hans-CN/index/introducing-gpt-5-2/. Benchlog https://benchlog.lekshome.cc/evidence/gpt-5-2/ev-gpt52-browsecomp/?lang=en
Related scores and conditions
GPT-5.2 · BrowseComp scores and configurations
Metric and score
Configuration and evaluation conditions
Evidence relation
Accuracy65.8%Reported 65.8% · Unit %
Published Unconfirmed
GPT-5.2 Thinking (xhigh)
Settings
Highest available API reasoning effort xhigh, except professional benchmark tasks.
Unknowns
none recorded
Tools
Tool access not recorded
Reasoning budget
xhigh
Framework
not recorded
Protocol
BrowseComp; article notes search blacklisting to reduce answer leakage.