Claude Opus 5.5 · FrontierCode(v1.1 Extended set) · 附件证据(ev-op55-card-frontiercode-extended)

Claude Opus 5.5 的 FrontierCode · v1.1 Extended set 官方出处。见《Claude Opus 5.5 System Card》§8.4, pp.176-177, Figures 8.4.A-B。证据 ev-op55-card-frontiercode-extended。

原文与定位

Claude Opus 5.5 · FrontierCode(v1.1 Extended set),FrontierCode v1.1 Extended medium effort配置,Overall score 65.3%(具体成绩公布时间未确认)。见《Claude Opus 5.5 System Card》§8.4, pp.176-177, Figures 8.4.A-B。 查看成绩条件

Claude Opus 5.5 · FrontierCode(v1.1 Extended set),FrontierCode v1.1 Extended max effort配置,Overall score 63.6%(具体成绩公布时间未确认)。见《Claude Opus 5.5 System Card》§8.4, pp.176-177, Figures 8.4.A-B。 查看成绩条件

Opus 5.5 ranks first on FrontierCode (Main) with a 54.6% score ... Opus 5.5 also ranks first on FrontierCode (Extended) with a 65.3% score ... highest ... at medium effort ... At max effort, Opus 5.5 scores 54.4% on Main and 63.6% on Extended.
官方材料
Claude Opus 5.5 System Card · PDF 第 176 页
定位
附件 · §8.4, pp.176-177, Figures 8.4.A-B
材料版本
官方当前 System Card;封面日期 2026-09-22;本地 PDF/TXT:本地留存副本、current-opus-5-5-system-card.txt;230 页全文核读;当前修订时间未知
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 5.5 · FrontierCode(v1.1 Extended set),FrontierCode v1.1 Extended medium effort配置,Overall score 65.3%(具体成绩公布时间未确认);Claude Opus 5.5 · FrontierCode(v1.1 Extended set),FrontierCode v1.1 Extended max effort配置,Overall score 63.6%(具体成绩公布时间未确认)。官方出处 Claude Opus 5.5 System Card(附件,官方当前 System Card;封面日期 2026-09-22;本地 PDF/TXT:本地留存副本、current-opus-5-5-system-card.txt;230 页全文核读;当前修订时间未知)§8.4, pp.176-177, Figures 8.4.A-B,https://www.anthropic.com/claude-opus-5-5-system-card#page=176。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5-5/ev-op55-card-frontiercode-extended/

关联成绩与条件

Claude Opus 5.5 · FrontierCode 成绩与配置
指标与成绩配置与评测条件证据关系
Overall score65.3%原文 65.3% · 单位 %
公布 未确认
FrontierCode v1.1 Extended medium effort
设置
Explicit medium effort; Cognition evaluation in Claude Code. Mean@5.
未知项
No API-equivalent harness or run date is stated.
工具
工具条件未记录
推理预算
medium
框架
Cognition Claude Code harness
协议
FrontierCode v1.1 Extended; Cognition Claude Code harness; mean@5; medium effort.
条件
Best reported effort. No timeout information is stated. The score is not a generic API result. Source-wide conditions: Cognition ran the evaluations in Claude Code; mean@5. Main and Extended are separate benchmark definitions.

直接支持该成绩

在排名中查看此成绩
Overall score63.6%原文 63.6% · 单位 %
公布 未确认
FrontierCode v1.1 Extended max effort
设置
Explicit max effort; Cognition evaluation in Claude Code. Mean@5.
未知项
No API-equivalent harness or run date is stated.
工具
工具条件未记录
推理预算
max
框架
Cognition Claude Code harness
协议
FrontierCode v1.1 Extended; Cognition Claude Code harness; mean@5; max effort.
条件
Distinct from medium-effort best score 65.3%; no timeout information is stated. Source-wide conditions: Cognition ran the evaluations in Claude Code; mean@5. Main and Extended are separate benchmark definitions.

直接支持该成绩

在排名中查看此成绩