Claude Opus 4.5 · AA-Omniscience(Anthropic factuality evaluation on 42 economically relevant topics across six domains; Claude Sonnet 4.5 grader; dataset revision not stated) · 附件证据(ev-op45-card-aa-omniscience)

Claude Opus 4.5 的 AA-Omniscience · Anthropic factuality evaluation on 42 economically relevant topics across six domains; Claude Sonnet 4.5 grader; dataset revision not stated 官方出处。见《Claude Opus 4.5 System Card》PDF pp.48, 51, §4.1 and Figure 4.1.C。证据 ev-op45-card-aa-omniscience。

原文与定位

Claude Opus 4.5 · AA-Omniscience(Anthropic factuality evaluation on 42 economically relevant topics across six domains; Claude Sonnet 4.5 grader; dataset revision not stated),Public factuality datasets, no thinking配置,Correct rate 43.7%(具体成绩公布时间未确认)。见《Claude Opus 4.5 System Card》PDF pp.48, 51, §4.1 and Figure 4.1.C。 查看成绩条件

Claude Opus 4.5 · AA-Omniscience(Anthropic factuality evaluation on 42 economically relevant topics across six domains; Claude Sonnet 4.5 grader; dataset revision not stated),Public factuality datasets, no thinking配置,Incorrect rate 36.7%(具体成绩公布时间未确认)。见《Claude Opus 4.5 System Card》PDF pp.48, 51, §4.1 and Figure 4.1.C。 查看成绩条件

Claude Opus 4.5 · AA-Omniscience(Anthropic factuality evaluation on 42 economically relevant topics across six domains; Claude Sonnet 4.5 grader; dataset revision not stated),Public factuality datasets, no thinking配置,Uncertain response rate 19.6%(具体成绩公布时间未确认)。见《Claude Opus 4.5 System Card》PDF pp.48, 51, §4.1 and Figure 4.1.C。 查看成绩条件

Claude Opus 4.5 · AA-Omniscience(Anthropic factuality evaluation on 42 economically relevant topics across six domains; Claude Sonnet 4.5 grader; dataset revision not stated),Public factuality datasets, 16K extended thinking配置,Correct rate 51.9%(具体成绩公布时间未确认)。见《Claude Opus 4.5 System Card》PDF pp.48, 51, §4.1 and Figure 4.1.C。 查看成绩条件

Claude Opus 4.5 · AA-Omniscience(Anthropic factuality evaluation on 42 economically relevant topics across six domains; Claude Sonnet 4.5 grader; dataset revision not stated),Public factuality datasets, 16K extended thinking配置,Incorrect rate 36.6%(具体成绩公布时间未确认)。见《Claude Opus 4.5 System Card》PDF pp.48, 51, §4.1 and Figure 4.1.C。 查看成绩条件

Claude Opus 4.5 · AA-Omniscience(Anthropic factuality evaluation on 42 economically relevant topics across six domains; Claude Sonnet 4.5 grader; dataset revision not stated),Public factuality datasets, 16K extended thinking配置,Uncertain response rate 11.5%(具体成绩公布时间未确认)。见《Claude Opus 4.5 System Card》PDF pp.48, 51, §4.1 and Figure 4.1.C。 查看成绩条件

AA-Omniscience correct / incorrect / uncertain rates for Opus 4.5: 43.7% / 36.7% / 19.6% without thinking; 51.9% / 36.6% / 11.5% with a 16K thinking budget. Claude Sonnet 4.5 graded answers.
官方材料
Claude Opus 4.5 System Card · PDF 第 51 页
定位
附件 · PDF pp.48, 51, §4.1 and Figure 4.1.C
材料版本
Current saved PDF/TXT: 本地留存副本 and .txt; cover November 2025, change log 2025-11-24; current binary is not established as launch-day bytes; fully reviewed 2026-11-16.
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

Claude Opus 4.5 · AA-Omniscience(Anthropic factuality evaluation on 42 economically relevant topics across six domains; Claude Sonnet 4.5 grader; dataset revision not stated),Public factuality datasets, no thinking配置,Correct rate 43.7%(具体成绩公布时间未确认);Claude Opus 4.5 · AA-Omniscience(Anthropic factuality evaluation on 42 economically relevant topics across six domains; Claude Sonnet 4.5 grader; dataset revision not stated),Public factuality datasets, no thinking配置,Incorrect rate 36.7%(具体成绩公布时间未确认);Claude Opus 4.5 · AA-Omniscience(Anthropic factuality evaluation on 42 economically relevant topics across six domains; Claude Sonnet 4.5 grader; dataset revision not stated),Public factuality datasets, no thinking配置,Uncertain response rate 19.6%(具体成绩公布时间未确认);Claude Opus 4.5 · AA-Omniscience(Anthropic factuality evaluation on 42 economically relevant topics across six domains; Claude Sonnet 4.5 grader; dataset revision not stated),Public factuality datasets, 16K extended thinking配置,Correct rate 51.9%(具体成绩公布时间未确认);Claude Opus 4.5 · AA-Omniscience(Anthropic factuality evaluation on 42 economically relevant topics across six domains; Claude Sonnet 4.5 grader; dataset revision not stated),Public factuality datasets, 16K extended thinking配置,Incorrect rate 36.6%(具体成绩公布时间未确认);Claude Opus 4.5 · AA-Omniscience(Anthropic factuality evaluation on 42 economically relevant topics across six domains; Claude Sonnet 4.5 grader; dataset revision not stated),Public factuality datasets, 16K extended thinking配置,Uncertain response rate 11.5%(具体成绩公布时间未确认)。官方出处 Claude Opus 4.5 System Card(附件,Current saved PDF/TXT: 本地留存副本 and .txt; cover November 2025, change log 2025-11-24; current binary is not established as launch-day bytes; fully reviewed 2026-11-16.)PDF pp.48, 51, §4.1 and Figure 4.1.C,https://www.anthropic.com/claude-opus-4-5-system-card#page=51。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-4-5/ev-op45-card-aa-omniscience/

关联成绩与条件

Claude Opus 4.5 · AA-Omniscience 成绩与配置
指标与成绩配置与评测条件证据关系
Correct rate43.7%原文 43.7% · 单位 %
公布 未确认
Public factuality datasets, no thinking
设置
No thinking; no external tools stated; Claude Sonnet 4.5 grades Simple-QA-Verified and AA-Omniscience.
未知项
Trial count and model sampling settings are not stated.
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
Anthropic evaluation on AA-Omniscience; correct rate; Sonnet 4.5 grader.
条件
No thinking; trial count and sampling settings not stated.

直接支持该成绩

在排名中查看此成绩
Incorrect rate36.7%原文 36.7% · 单位 %
公布 未确认
Public factuality datasets, no thinking
设置
No thinking; no external tools stated; Claude Sonnet 4.5 grades Simple-QA-Verified and AA-Omniscience.
未知项
Trial count and model sampling settings are not stated.
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
Anthropic evaluation on AA-Omniscience; incorrect rate; Sonnet 4.5 grader.
条件
No thinking; trial count and sampling settings not stated.

直接支持该成绩

在排名中查看此成绩
Uncertain response rate19.6%原文 19.6% · 单位 %
公布 未确认
Public factuality datasets, no thinking
设置
No thinking; no external tools stated; Claude Sonnet 4.5 grades Simple-QA-Verified and AA-Omniscience.
未知项
Trial count and model sampling settings are not stated.
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
Anthropic evaluation on AA-Omniscience; uncertain response rate; Sonnet 4.5 grader.
条件
No thinking; trial count and sampling settings not stated.

直接支持该成绩

在排名中查看此成绩
Correct rate51.9%原文 51.9% · 单位 %
公布 未确认
Public factuality datasets, 16K extended thinking
设置
16K extended-thinking budget; no external tools stated; Claude Sonnet 4.5 grades Simple-QA-Verified and AA-Omniscience.
未知项
Trial count and model sampling settings are not stated.
工具
工具条件未记录
推理预算
思考预算 16K
框架
未记录
协议
Anthropic evaluation on AA-Omniscience; correct rate; Sonnet 4.5 grader.
条件
16K extended-thinking budget; trial count and sampling settings not stated.

直接支持该成绩

在排名中查看此成绩
Incorrect rate36.6%原文 36.6% · 单位 %
公布 未确认
Public factuality datasets, 16K extended thinking
设置
16K extended-thinking budget; no external tools stated; Claude Sonnet 4.5 grades Simple-QA-Verified and AA-Omniscience.
未知项
Trial count and model sampling settings are not stated.
工具
工具条件未记录
推理预算
思考预算 16K
框架
未记录
协议
Anthropic evaluation on AA-Omniscience; incorrect rate; Sonnet 4.5 grader.
条件
16K extended-thinking budget; trial count and sampling settings not stated.

直接支持该成绩

在排名中查看此成绩
Uncertain response rate11.5%原文 11.5% · 单位 %
公布 未确认
Public factuality datasets, 16K extended thinking
设置
16K extended-thinking budget; no external tools stated; Claude Sonnet 4.5 grades Simple-QA-Verified and AA-Omniscience.
未知项
Trial count and model sampling settings are not stated.
工具
工具条件未记录
推理预算
思考预算 16K
框架
未记录
协议
Anthropic evaluation on AA-Omniscience; uncertain response rate; Sonnet 4.5 grader.
条件
16K extended-thinking budget; trial count and sampling settings not stated.

直接支持该成绩

在排名中查看此成绩