Claude Opus 4.7 · GDPval-AA(Artificial Analysis leaderboard) 1753 Elo · 附件证据(ev-op47-card-gdpval-aa)

Claude Opus 4.7 的 GDPval-AA · Artificial Analysis leaderboard 官方出处。GDPval-AA独立Elo评测 · 1753 Elo。见《Claude Opus 4.7 System Card》§8.10.5 and Figure 8.10.5.A, PDF p.211。证据 ev-op47-card-gdpval-aa。

原文与定位

Claude Opus 4.7 · GDPval-AA(Artificial Analysis leaderboard),GDPval-AA独立Elo评测配置,Elo rating 1753 Elo(具体成绩公布时间未确认)。见《Claude Opus 4.7 System Card》§8.10.5 and Figure 8.10.5.A, PDF p.211。 查看成绩条件

The GDPval-AA Elo bar is explicitly labeled 1,753. The evaluation was run independently by Artificial Analysis over 220 tasks across 44 occupations and 9 industries.
官方材料
Claude Opus 4.7 System Card · PDF 第 211 页
定位
附件 · §8.10.5 and Figure 8.10.5.A, PDF p.211
材料版本
Current saved PDF/TXT: 本地留存副本 and current-opus-4-7-system-card.txt; 232 PDF pages; metadata created/modified 2026-04-16 22:11:48 China Standard Time. Full current-card review completed 2026-11-16; this file is not established as launch-day bytes.
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 4.7 · GDPval-AA(Artificial Analysis leaderboard),GDPval-AA独立Elo评测配置,Elo rating 1753 Elo(具体成绩公布时间未确认)。官方出处 Claude Opus 4.7 System Card(附件,Current saved PDF/TXT: 本地留存副本 and current-opus-4-7-system-card.txt; 232 PDF pages; metadata created/modified 2026-04-16 22:11:48 China Standard Time. Full current-card review completed 2026-11-16; this file is not established as launch-day bytes.)§8.10.5 and Figure 8.10.5.A, PDF p.211,https://www.anthropic.com/claude-opus-4-7-system-card#page=211。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-4-7/ev-op47-card-gdpval-aa/

关联成绩与条件

Claude Opus 4.7 · GDPval-AA 成绩与配置
指标与成绩配置与评测条件证据关系
Elo rating1753 Elo原文 1,753 Elo · 单位 Elo
公布 未确认
GDPval-AA独立Elo评测
设置
Artificial Analysis independent evaluation; 220 GDPval tasks across 44 occupations and 9 industries; agent has shell and web browsing; blind pairwise output comparisons.
未知项
未另记
工具
允许工具
推理预算
未记录
框架
未记录
协议
GDPval-AA independent Elo evaluation.
条件
Artificial Analysis evaluation over 220 GDPval tasks, 44 occupations and 9 industries; shell and web access; blind pairwise comparisons.

直接支持该成绩