Claude Sonnet 5.5 · WANDR(500-task wide research benchmark),Low effort配置,Soft F1 10%(具体成绩公布时间未确认)。见《Claude Sonnet 5.5 System Card》§8.11.3, Figure 8.11.3.A, PDF p.122; chart-label transcription。 查看成绩条件
Claude Sonnet 5.5 · WANDR(500-task wide research benchmark),Medium effort配置,Soft F1 29.9%(具体成绩公布时间未确认)。见《Claude Sonnet 5.5 System Card》§8.11.3, Figure 8.11.3.A, PDF p.122; chart-label transcription。 查看成绩条件
Claude Sonnet 5.5 · WANDR(500-task wide research benchmark),High effort配置,Soft F1 56.3%(具体成绩公布时间未确认)。见《Claude Sonnet 5.5 System Card》§8.11.3, Figure 8.11.3.A, PDF p.122; chart-label transcription。 查看成绩条件
Claude Sonnet 5.5 · WANDR(500-task wide research benchmark),Xhigh effort配置,Soft F1 66.6%(具体成绩公布时间未确认)。见《Claude Sonnet 5.5 System Card》§8.11.3, Figure 8.11.3.A, PDF p.122; chart-label transcription。 查看成绩条件
Claude Sonnet 5.5 · WANDR(500-task wide research benchmark),Max effort配置,Soft F1 70%(具体成绩公布时间未确认)。见《Claude Sonnet 5.5 System Card》§8.11.3, Figure 8.11.3.A, PDF p.122; chart-label transcription。 查看成绩条件
Claude Sonnet 5.5: Low 10.0%; Med 29.9%; High 56.3%; Xhigh 66.6%; Max 70.0%.
附件 · §8.11.3, Figure 8.11.3.A, PDF p.122; chart-label transcription
材料版本
PDF cover dated 2026-09-28; 148 pages; collected 2026-11-10
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 Sonnet 5.5 · WANDR(500-task wide research benchmark),Low effort配置,Soft F1 10%(具体成绩公布时间未确认);Claude Sonnet 5.5 · WANDR(500-task wide research benchmark),Medium effort配置,Soft F1 29.9%(具体成绩公布时间未确认);Claude Sonnet 5.5 · WANDR(500-task wide research benchmark),High effort配置,Soft F1 56.3%(具体成绩公布时间未确认);Claude Sonnet 5.5 · WANDR(500-task wide research benchmark),Xhigh effort配置,Soft F1 66.6%(具体成绩公布时间未确认);Claude Sonnet 5.5 · WANDR(500-task wide research benchmark),Max effort配置,Soft F1 70%(具体成绩公布时间未确认)。官方出处 Claude Sonnet 5.5 System Card(附件,PDF cover dated 2026-09-28; 148 pages; collected 2026-11-10)§8.11.3, Figure 8.11.3.A, PDF p.122; chart-label transcription,https://www.anthropic.com/claude-sonnet-5-5-system-card#page=122。Benchlog https://benchlog.lekshome.cc/evidence/claude-sonnet-5-5/ev55-visual-wandr-effort/
关联成绩与条件
Claude Sonnet 5.5 · WANDR 成绩与配置
指标与成绩
配置与评测条件
证据关系
Soft F110%原文 10.0% · 单位 %
公布 未确认
Low effort
设置
Low reasoning effort.
未知项
Sampling settings not stated unless recorded per result.
工具
允许工具
推理预算
low
框架
未记录
协议
WANDR, 500 tasks; soft F1 averaged across tasks.
条件
Figure labels the effort Low; offline web search and web fetch over a frozen index; Claude Opus 4.6 grader; 980k-token task budget. The report says the modified tools and grading differ from Perplexity's harness.
Sampling settings not stated unless recorded per result.
工具
允许工具
推理预算
med
框架
未记录
协议
WANDR, 500 tasks; soft F1 averaged across tasks.
条件
Figure labels the effort Med; offline web search and web fetch over a frozen index; Claude Opus 4.6 grader; 980k-token task budget. The report says the modified tools and grading differ from Perplexity's harness.
Sampling settings not stated unless recorded per result.
工具
允许工具
推理预算
high
框架
未记录
协议
WANDR, 500 tasks; soft F1 averaged across tasks.
条件
Figure labels the effort High; offline web search and web fetch over a frozen index; Claude Opus 4.6 grader; 980k-token task budget. The report says the modified tools and grading differ from Perplexity's harness.
Sampling settings not stated unless recorded per result.
工具
允许工具
推理预算
xhigh
框架
未记录
协议
WANDR, 500 tasks; soft F1 averaged across tasks.
条件
Figure labels the effort Xhigh; offline web search and web fetch over a frozen index; Claude Opus 4.6 grader; 980k-token task budget. The report says the modified tools and grading differ from Perplexity's harness.
Figure labels the effort Max; offline web search and web fetch over a frozen index; Claude Opus 4.6 grader; 980k-token task budget. The report says the modified tools and grading differ from Perplexity's harness.
Claude Sonnet 5.5 · WANDR (500-task wide research benchmark) · Attachment evidence (ev55-visual-wandr-effort)
Official source for WANDR · 500-task wide research benchmark in Claude Sonnet 5.5. See “Claude Sonnet 5.5 System Card” at §8.11.3, Figure 8.11.3.A, PDF p.122; chart-label transcription. Evidence ev55-visual-wandr-effort.
Claude Sonnet 5.5 · WANDR (500-task wide research benchmark), configuration Low effort, Soft F1 10% (exact score publication date unconfirmed). See “Claude Sonnet 5.5 System Card” at §8.11.3, Figure 8.11.3.A, PDF p.122; chart-label transcription. View score conditions
Claude Sonnet 5.5 · WANDR (500-task wide research benchmark), configuration Medium effort, Soft F1 29.9% (exact score publication date unconfirmed). See “Claude Sonnet 5.5 System Card” at §8.11.3, Figure 8.11.3.A, PDF p.122; chart-label transcription. View score conditions
Claude Sonnet 5.5 · WANDR (500-task wide research benchmark), configuration High effort, Soft F1 56.3% (exact score publication date unconfirmed). See “Claude Sonnet 5.5 System Card” at §8.11.3, Figure 8.11.3.A, PDF p.122; chart-label transcription. View score conditions
Claude Sonnet 5.5 · WANDR (500-task wide research benchmark), configuration Xhigh effort, Soft F1 66.6% (exact score publication date unconfirmed). See “Claude Sonnet 5.5 System Card” at §8.11.3, Figure 8.11.3.A, PDF p.122; chart-label transcription. View score conditions
Claude Sonnet 5.5 · WANDR (500-task wide research benchmark), configuration Max effort, Soft F1 70% (exact score publication date unconfirmed). See “Claude Sonnet 5.5 System Card” at §8.11.3, Figure 8.11.3.A, PDF p.122; chart-label transcription. View score conditions
Claude Sonnet 5.5: Low 10.0%; Med 29.9%; High 56.3%; Xhigh 66.6%; Max 70.0%.
Attachment · §8.11.3, Figure 8.11.3.A, PDF p.122; chart-label transcription
Material version
PDF cover dated 2026-09-28; 148 pages; collected 2026-11-10
Version published
Unconfirmed
Disclosure date
Unconfirmed · Launch or later disclosure unconfirmed
Collected
Historical basis
No reliable historical version evidence available
Citation text
Claude Sonnet 5.5 · WANDR (500-task wide research benchmark), configuration Low effort, Soft F1 10% (exact score publication date unconfirmed); Claude Sonnet 5.5 · WANDR (500-task wide research benchmark), configuration Medium effort, Soft F1 29.9% (exact score publication date unconfirmed); Claude Sonnet 5.5 · WANDR (500-task wide research benchmark), configuration High effort, Soft F1 56.3% (exact score publication date unconfirmed); Claude Sonnet 5.5 · WANDR (500-task wide research benchmark), configuration Xhigh effort, Soft F1 66.6% (exact score publication date unconfirmed); Claude Sonnet 5.5 · WANDR (500-task wide research benchmark), configuration Max effort, Soft F1 70% (exact score publication date unconfirmed). Official source: Claude Sonnet 5.5 System Card (Attachment, PDF cover dated 2026-09-28; 148 pages; collected 2026-11-10), §8.11.3, Figure 8.11.3.A, PDF p.122; chart-label transcription, https://www.anthropic.com/claude-sonnet-5-5-system-card#page=122. Benchlog https://benchlog.lekshome.cc/evidence/claude-sonnet-5-5/ev55-visual-wandr-effort/?lang=en
Related scores and conditions
Claude Sonnet 5.5 · WANDR scores and configurations
Metric and score
Configuration and evaluation conditions
Evidence relation
Soft F110%Reported 10.0% · Unit %
Published Unconfirmed
Low effort
Settings
Low reasoning effort.
Unknowns
Sampling settings not stated unless recorded per result.
Tools
Tools allowed
Reasoning budget
low
Framework
not recorded
Protocol
WANDR, 500 tasks; soft F1 averaged across tasks.
Conditions
Figure labels the effort Low; offline web search and web fetch over a frozen index; Claude Opus 4.6 grader; 980k-token task budget. The report says the modified tools and grading differ from Perplexity's harness.
Sampling settings not stated unless recorded per result.
Tools
Tools allowed
Reasoning budget
med
Framework
not recorded
Protocol
WANDR, 500 tasks; soft F1 averaged across tasks.
Conditions
Figure labels the effort Med; offline web search and web fetch over a frozen index; Claude Opus 4.6 grader; 980k-token task budget. The report says the modified tools and grading differ from Perplexity's harness.
Sampling settings not stated unless recorded per result.
Tools
Tools allowed
Reasoning budget
high
Framework
not recorded
Protocol
WANDR, 500 tasks; soft F1 averaged across tasks.
Conditions
Figure labels the effort High; offline web search and web fetch over a frozen index; Claude Opus 4.6 grader; 980k-token task budget. The report says the modified tools and grading differ from Perplexity's harness.
Sampling settings not stated unless recorded per result.
Tools
Tools allowed
Reasoning budget
xhigh
Framework
not recorded
Protocol
WANDR, 500 tasks; soft F1 averaged across tasks.
Conditions
Figure labels the effort Xhigh; offline web search and web fetch over a frozen index; Claude Opus 4.6 grader; 980k-token task budget. The report says the modified tools and grading differ from Perplexity's harness.
Figure labels the effort Max; offline web search and web fetch over a frozen index; Claude Opus 4.6 grader; 980k-token task budget. The report says the modified tools and grading differ from Perplexity's harness.