Claude Opus 4.5 · Simple-QA-Verified(Anthropic factuality evaluation; Claude Sonnet 4.5 grader; exact dataset revision not stated) · 附件证据(ev-op45-card-simpleqa)

Claude Opus 4.5 的 Simple-QA-Verified · Anthropic factuality evaluation; Claude Sonnet 4.5 grader; exact dataset revision not stated 官方出处。见《Claude Opus 4.5 System Card》PDF pp.48, 50, §4.1 and Figure 4.1.B。证据 ev-op45-card-simpleqa。

原文与定位

Claude Opus 4.5 · Simple-QA-Verified(Anthropic factuality evaluation; Claude Sonnet 4.5 grader; exact dataset revision not stated),Public factuality datasets, no thinking配置,Correct rate 33.1%(具体成绩公布时间未确认)。见《Claude Opus 4.5 System Card》PDF pp.48, 50, §4.1 and Figure 4.1.B。 查看成绩条件

Claude Opus 4.5 · Simple-QA-Verified(Anthropic factuality evaluation; Claude Sonnet 4.5 grader; exact dataset revision not stated),Public factuality datasets, no thinking配置,Incorrect rate 36.4%(具体成绩公布时间未确认)。见《Claude Opus 4.5 System Card》PDF pp.48, 50, §4.1 and Figure 4.1.B。 查看成绩条件

Claude Opus 4.5 · Simple-QA-Verified(Anthropic factuality evaluation; Claude Sonnet 4.5 grader; exact dataset revision not stated),Public factuality datasets, no thinking配置,Uncertain response rate 30.6%(具体成绩公布时间未确认)。见《Claude Opus 4.5 System Card》PDF pp.48, 50, §4.1 and Figure 4.1.B。 查看成绩条件

Claude Opus 4.5 · Simple-QA-Verified(Anthropic factuality evaluation; Claude Sonnet 4.5 grader; exact dataset revision not stated),Public factuality datasets, 16K extended thinking配置,Correct rate 44.1%(具体成绩公布时间未确认)。见《Claude Opus 4.5 System Card》PDF pp.48, 50, §4.1 and Figure 4.1.B。 查看成绩条件

Claude Opus 4.5 · Simple-QA-Verified(Anthropic factuality evaluation; Claude Sonnet 4.5 grader; exact dataset revision not stated),Public factuality datasets, 16K extended thinking配置,Incorrect rate 35.4%(具体成绩公布时间未确认)。见《Claude Opus 4.5 System Card》PDF pp.48, 50, §4.1 and Figure 4.1.B。 查看成绩条件

Claude Opus 4.5 · Simple-QA-Verified(Anthropic factuality evaluation; Claude Sonnet 4.5 grader; exact dataset revision not stated),Public factuality datasets, 16K extended thinking配置,Uncertain response rate 20.5%(具体成绩公布时间未确认)。见《Claude Opus 4.5 System Card》PDF pp.48, 50, §4.1 and Figure 4.1.B。 查看成绩条件

Simple-QA-Verified correct / incorrect / uncertain rates for Opus 4.5: 33.1% / 36.4% / 30.6% without thinking; 44.1% / 35.4% / 20.5% with a 16K extended-thinking budget. Claude Sonnet 4.5 graded answers.
官方材料
Claude Opus 4.5 System Card · PDF 第 50 页
定位
附件 · PDF pp.48, 50, §4.1 and Figure 4.1.B
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 · Simple-QA-Verified(Anthropic factuality evaluation; Claude Sonnet 4.5 grader; exact dataset revision not stated),Public factuality datasets, no thinking配置,Correct rate 33.1%(具体成绩公布时间未确认);Claude Opus 4.5 · Simple-QA-Verified(Anthropic factuality evaluation; Claude Sonnet 4.5 grader; exact dataset revision not stated),Public factuality datasets, no thinking配置,Incorrect rate 36.4%(具体成绩公布时间未确认);Claude Opus 4.5 · Simple-QA-Verified(Anthropic factuality evaluation; Claude Sonnet 4.5 grader; exact dataset revision not stated),Public factuality datasets, no thinking配置,Uncertain response rate 30.6%(具体成绩公布时间未确认);Claude Opus 4.5 · Simple-QA-Verified(Anthropic factuality evaluation; Claude Sonnet 4.5 grader; exact dataset revision not stated),Public factuality datasets, 16K extended thinking配置,Correct rate 44.1%(具体成绩公布时间未确认);Claude Opus 4.5 · Simple-QA-Verified(Anthropic factuality evaluation; Claude Sonnet 4.5 grader; exact dataset revision not stated),Public factuality datasets, 16K extended thinking配置,Incorrect rate 35.4%(具体成绩公布时间未确认);Claude Opus 4.5 · Simple-QA-Verified(Anthropic factuality evaluation; Claude Sonnet 4.5 grader; exact dataset revision not stated),Public factuality datasets, 16K extended thinking配置,Uncertain response rate 20.5%(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, 50, §4.1 and Figure 4.1.B,https://www.anthropic.com/claude-opus-4-5-system-card#page=50。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-4-5/ev-op45-card-simpleqa/

关联成绩与条件

Claude Opus 4.5 · Simple-QA-Verified 成绩与配置
指标与成绩配置与评测条件证据关系
Correct rate33.1%原文 33.1% · 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 Simple-QA-Verified factuality evaluation; 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 rate36.4%原文 36.4% · 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 Simple-QA-Verified factuality evaluation; 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 rate30.6%原文 30.6% · 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 Simple-QA-Verified factuality evaluation; 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 rate44.1%原文 44.1% · 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 Simple-QA-Verified factuality evaluation; 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 rate35.4%原文 35.4% · 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 Simple-QA-Verified factuality evaluation; 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 rate20.5%原文 20.5% · 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 Simple-QA-Verified factuality evaluation; 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