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
| 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
| 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
| 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
| 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
| 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
| 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
| 直接支持该成绩 在排名中查看此成绩 |