Claude Opus 5 · DRACO(100-task Perplexity deep-research benchmark) · 附件证据(ev-op5-card-draco)

Claude Opus 5 的 DRACO · 100-task Perplexity deep-research benchmark 官方出处。见《Claude Opus 5 System Card》System Card PDF p.166, Figure 8.10.4.A; Opus 5 series labels。证据 ev-op5-card-draco。

原文与定位

Claude Opus 5 · DRACO(100-task Perplexity deep-research benchmark),DRACO · Low effort配置,Normalized score 83.2%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF p.166, Figure 8.10.4.A; Opus 5 series labels。 查看成绩条件

Claude Opus 5 · DRACO(100-task Perplexity deep-research benchmark),DRACO · Medium effort配置,Normalized score 86.8%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF p.166, Figure 8.10.4.A; Opus 5 series labels。 查看成绩条件

Claude Opus 5 · DRACO(100-task Perplexity deep-research benchmark),DRACO · High effort配置,Normalized score 87%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF p.166, Figure 8.10.4.A; Opus 5 series labels。 查看成绩条件

Claude Opus 5 · DRACO(100-task Perplexity deep-research benchmark),DRACO · Xhigh effort配置,Normalized score 88.1%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF p.166, Figure 8.10.4.A; Opus 5 series labels。 查看成绩条件

Claude Opus 5 · DRACO(100-task Perplexity deep-research benchmark),DRACO · Max effort配置,Normalized score 88.6%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF p.166, Figure 8.10.4.A; Opus 5 series labels。 查看成绩条件

视觉转录(Claude Opus 5 图中明确标注):Normalized DRACO score: low 83.2%; medium 86.8%; high 87.0%; xhigh 88.1%; max 88.6%. Figure states a 980K-token budget.
官方材料
Claude Opus 5 System Card · PDF 第 166 页
定位
附件 · System Card PDF p.166, Figure 8.10.4.A; Opus 5 series labels
材料版本
Current saved PDF/TXT: 本地留存副本 and current-opus-5-system-card.txt; cover dated 2026-07-24; p.2 changelog records an update on 2026-08-19; later revision date, if any, unknown.
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 · DRACO(100-task Perplexity deep-research benchmark),DRACO · Low effort配置,Normalized score 83.2%(具体成绩公布时间未确认);Claude Opus 5 · DRACO(100-task Perplexity deep-research benchmark),DRACO · Medium effort配置,Normalized score 86.8%(具体成绩公布时间未确认);Claude Opus 5 · DRACO(100-task Perplexity deep-research benchmark),DRACO · High effort配置,Normalized score 87%(具体成绩公布时间未确认);Claude Opus 5 · DRACO(100-task Perplexity deep-research benchmark),DRACO · Xhigh effort配置,Normalized score 88.1%(具体成绩公布时间未确认);Claude Opus 5 · DRACO(100-task Perplexity deep-research benchmark),DRACO · Max effort配置,Normalized score 88.6%(具体成绩公布时间未确认)。官方出处 Claude Opus 5 System Card(附件,Current saved PDF/TXT: 本地留存副本 and current-opus-5-system-card.txt; cover dated 2026-07-24; p.2 changelog records an update on 2026-08-19; later revision date, if any, unknown.)System Card PDF p.166, Figure 8.10.4.A; Opus 5 series labels,https://www.anthropic.com/claude-opus-5-system-card#page=166。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5/ev-op5-card-draco/

关联成绩与条件

Claude Opus 5 · DRACO 成绩与配置
指标与成绩配置与评测条件证据关系
Normalized score83.2%原文 83.2% · 单位 %
公布 未确认
DRACO · Low effort
设置
100 curated deep-research tasks; web search, web fetch, programmatic tool calling, and code execution; figure states a 980K-token budget; Opus 4.6 grades reports written to a file using the paper formula. Explicit adaptive-thinking effort: low.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
工具
允许工具
推理预算
low
框架
未记录
协议
DRACO; normalized score over 100 curated tasks; Opus 4.6 grader; report-file protocol.
条件
Explicit effort labels; figure budget 980K tokens; web search, fetch, programmatic tools and code execution; judge model and report-file scoring differ from original paper, so headline scores are not directly comparable.

直接支持该成绩

在排名中查看此成绩
Normalized score86.8%原文 86.8% · 单位 %
公布 未确认
DRACO · Medium effort
设置
100 curated deep-research tasks; web search, web fetch, programmatic tool calling, and code execution; figure states a 980K-token budget; Opus 4.6 grades reports written to a file using the paper formula. Explicit adaptive-thinking effort: medium.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
工具
允许工具
推理预算
medium
框架
未记录
协议
DRACO; normalized score over 100 curated tasks; Opus 4.6 grader; report-file protocol.
条件
Explicit effort labels; figure budget 980K tokens; web search, fetch, programmatic tools and code execution; judge model and report-file scoring differ from original paper, so headline scores are not directly comparable.

直接支持该成绩

在排名中查看此成绩
Normalized score87%原文 87% · 单位 %
公布 未确认
DRACO · High effort
设置
100 curated deep-research tasks; web search, web fetch, programmatic tool calling, and code execution; figure states a 980K-token budget; Opus 4.6 grades reports written to a file using the paper formula. Explicit adaptive-thinking effort: high.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
工具
允许工具
推理预算
high
框架
未记录
协议
DRACO; normalized score over 100 curated tasks; Opus 4.6 grader; report-file protocol.
条件
Explicit effort labels; figure budget 980K tokens; web search, fetch, programmatic tools and code execution; judge model and report-file scoring differ from original paper, so headline scores are not directly comparable.

直接支持该成绩

在排名中查看此成绩
Normalized score88.1%原文 88.1% · 单位 %
公布 未确认
DRACO · Xhigh effort
设置
100 curated deep-research tasks; web search, web fetch, programmatic tool calling, and code execution; figure states a 980K-token budget; Opus 4.6 grades reports written to a file using the paper formula. Explicit adaptive-thinking effort: xhigh.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
工具
允许工具
推理预算
xhigh
框架
未记录
协议
DRACO; normalized score over 100 curated tasks; Opus 4.6 grader; report-file protocol.
条件
Explicit effort labels; figure budget 980K tokens; web search, fetch, programmatic tools and code execution; judge model and report-file scoring differ from original paper, so headline scores are not directly comparable.

直接支持该成绩

在排名中查看此成绩
Normalized score88.6%原文 88.6% · 单位 %
公布 未确认
DRACO · Max effort
设置
100 curated deep-research tasks; web search, web fetch, programmatic tool calling, and code execution; figure states a 980K-token budget; Opus 4.6 grades reports written to a file using the paper formula. Explicit adaptive-thinking effort: max.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
工具
允许工具
推理预算
max
框架
未记录
协议
DRACO; normalized score over 100 curated tasks; Opus 4.6 grader; report-file protocol.
条件
Explicit effort labels; figure budget 980K tokens; web search, fetch, programmatic tools and code execution; judge model and report-file scoring differ from original paper, so headline scores are not directly comparable.

直接支持该成绩

在排名中查看此成绩