Claude Fable 5.2 · DRACO(100-task Perplexity deep-research benchmark) · 附件证据(ev-f52-draco-scaling)

Claude Fable 5.2 的 DRACO · 100-task Perplexity deep-research benchmark 官方出处。见《Claude Fable 5.2 and Claude Mythos 5.2 System Card》PDF p.219, Figure 8.11.2.A, DRACO(已渲染并视觉核读数值标签)。证据 ev-f52-draco-scaling。

原文与定位

Claude Fable 5.2 · DRACO(100-task Perplexity deep-research benchmark),Low effort配置,Normalized score 81.6%(具体成绩公布时间未确认)。见《Claude Fable 5.2 and Claude Mythos 5.2 System Card》PDF p.219, Figure 8.11.2.A, DRACO(已渲染并视觉核读数值标签)。 查看成绩条件

Claude Fable 5.2 · DRACO(100-task Perplexity deep-research benchmark),Medium effort配置,Normalized score 82.2%(具体成绩公布时间未确认)。见《Claude Fable 5.2 and Claude Mythos 5.2 System Card》PDF p.219, Figure 8.11.2.A, DRACO(已渲染并视觉核读数值标签)。 查看成绩条件

Claude Fable 5.2 · DRACO(100-task Perplexity deep-research benchmark),High effort配置,Normalized score 84.1%(具体成绩公布时间未确认)。见《Claude Fable 5.2 and Claude Mythos 5.2 System Card》PDF p.219, Figure 8.11.2.A, DRACO(已渲染并视觉核读数值标签)。 查看成绩条件

Claude Fable 5.2 · DRACO(100-task Perplexity deep-research benchmark),Xhigh effort配置,Normalized score 85.2%(具体成绩公布时间未确认)。见《Claude Fable 5.2 and Claude Mythos 5.2 System Card》PDF p.219, Figure 8.11.2.A, DRACO(已渲染并视觉核读数值标签)。 查看成绩条件

Claude Fable 5.2 · DRACO(100-task Perplexity deep-research benchmark),Adaptive Max配置,Normalized score 87.7%(具体成绩公布时间未确认)。见《Claude Fable 5.2 and Claude Mythos 5.2 System Card》PDF p.219, Figure 8.11.2.A, DRACO(已渲染并视觉核读数值标签)。 查看成绩条件

Visually labeled normalized DRACO scores: 81.6% low, 82.2% medium, 84.1% high, 85.2% xhigh, and 87.7% max; 980k-token task budget.
官方材料
Claude Fable 5.2 and Claude Mythos 5.2 System Card · PDF 第 219 页
定位
附件 · PDF p.219, Figure 8.11.2.A, DRACO(已渲染并视觉核读数值标签)
材料版本
Official System Card; 264-page PDF, cover dated November 9, 2026; current PDF/TXT saved as 本地留存副本 and .txt; PDF pp.1-264 text read page-by-page; all 80 image/vector-figure pages in pp.1-206 were visually checked in 21 sheets, and capability figures in pp.207-254 were visually checked; no unread pages or figures remain.
版本公布
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 Fable 5.2 · DRACO(100-task Perplexity deep-research benchmark),Low effort配置,Normalized score 81.6%(具体成绩公布时间未确认);Claude Fable 5.2 · DRACO(100-task Perplexity deep-research benchmark),Medium effort配置,Normalized score 82.2%(具体成绩公布时间未确认);Claude Fable 5.2 · DRACO(100-task Perplexity deep-research benchmark),High effort配置,Normalized score 84.1%(具体成绩公布时间未确认);Claude Fable 5.2 · DRACO(100-task Perplexity deep-research benchmark),Xhigh effort配置,Normalized score 85.2%(具体成绩公布时间未确认);Claude Fable 5.2 · DRACO(100-task Perplexity deep-research benchmark),Adaptive Max配置,Normalized score 87.7%(具体成绩公布时间未确认)。官方出处 Claude Fable 5.2 and Claude Mythos 5.2 System Card(附件,Official System Card; 264-page PDF, cover dated November 9, 2026; current PDF/TXT saved as 本地留存副本 and .txt; PDF pp.1-264 text read page-by-page; all 80 image/vector-figure pages in pp.1-206 were visually checked in 21 sheets, and capability figures in pp.207-254 were visually checked; no unread pages or figures remain.)PDF p.219, Figure 8.11.2.A, DRACO(已渲染并视觉核读数值标签),https://www.anthropic.com/document/claude-fable-5-2-mythos-5-2-system-card#page=219。Benchlog https://benchlog.lekshome.cc/evidence/claude-fable-and-mythos-5-2/ev-f52-draco-scaling/

关联成绩与条件

Claude Fable 5.2 · DRACO 成绩与配置
指标与成绩配置与评测条件证据关系
Normalized score81.6%原文 81.6% · 单位 %
公布 未确认
Low effort
设置
Claude Fable 5.2;adaptive thinking always on;Low effort。
未知项
未另记
工具
允许工具
推理预算
low
框架
未记录
协议
DRACO 100-task set; low effort; web search/fetch, programmatic tool calling, code execution; 980k-token budget.
条件
Claude Opus 4.6 grader; five independent grading runs per response and mean reported; only final report file graded; not directly comparable to paper scores.

直接支持该成绩

在排名中查看此成绩
Normalized score82.2%原文 82.2% · 单位 %
公布 未确认
Medium effort
设置
Claude Fable 5.2;adaptive thinking always on;Medium effort。
未知项
主文未列该配置的采样设置与运行数。
工具
允许工具
推理预算
medium
框架
未记录
协议
DRACO 100-task set; medium effort; web search/fetch, programmatic tool calling, code execution; 980k-token budget.
条件
Claude Opus 4.6 grader; five independent grading runs per response and mean reported; only final report file graded; not directly comparable to paper scores.

直接支持该成绩

在排名中查看此成绩
Normalized score84.1%原文 84.1% · 单位 %
公布 未确认
High effort
设置
Claude Fable 5.2;adaptive thinking always on;High effort。
未知项
主文未列该配置的采样设置与运行数。
工具
允许工具
推理预算
high
框架
未记录
协议
DRACO 100-task set; high effort; web search/fetch, programmatic tool calling, code execution; 980k-token budget.
条件
Claude Opus 4.6 grader; five independent grading runs per response and mean reported; only final report file graded; not directly comparable to paper scores.

直接支持该成绩

在排名中查看此成绩
Normalized score85.2%原文 85.2% · 单位 %
公布 未确认
Xhigh effort
设置
Claude Fable 5.2;adaptive thinking always on;Xhigh effort。
未知项
主文未列该配置的采样设置与运行数。
工具
允许工具
推理预算
xhigh
框架
未记录
协议
DRACO 100-task set; xhigh effort; web search/fetch, programmatic tool calling, code execution; 980k-token budget.
条件
Claude Opus 4.6 grader; five independent grading runs per response and mean reported; only final report file graded; not directly comparable to paper scores.

直接支持该成绩

在排名中查看此成绩
Normalized score87.7%原文 87.7% · 单位 %
公布 未确认
Adaptive Max
设置
Claude Fable 5.2;adaptive thinking always on;Max effort;默认 temperature/top_p;Card 通用表说明通常五次运行平均,个别测试另行注明。
未知项
System Card pp.1-264 文字已完整核读;各benchmark章节未明确披露的运行参数仍未知。
工具
允许工具
推理预算
max
框架
未记录
协议
DRACO 100-task set; max effort; web search/fetch, programmatic tool calling, code execution; 980k-token budget.
条件
Claude Opus 4.6 grader; five independent grading runs per response and mean reported; only final report file graded; not directly comparable to paper scores.

直接支持该成绩

在排名中查看此成绩