Claude Opus 5 · DeepSearchQA(900 prompts;单代理与多代理按协议区分) · 附件证据(ev-op5-card-deepsearchqa)
Claude Opus 5 的 DeepSearchQA · 900 prompts;单代理与多代理按协议区分 官方出处。见《Claude Opus 5 System Card》System Card PDF p.165, Figure 8.10.3.A; Opus 5 series labels。证据 ev-op5-card-deepsearchqa。
Claude Opus 5 · DeepSearchQA(900 prompts;单代理与多代理按协议区分),DeepSearchQA · Low effort配置,F1 score 91%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF p.165, Figure 8.10.3.A; Opus 5 series labels。 查看成绩条件
Claude Opus 5 · DeepSearchQA(900 prompts;单代理与多代理按协议区分),DeepSearchQA · Medium effort配置,F1 score 92.8%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF p.165, Figure 8.10.3.A; Opus 5 series labels。 查看成绩条件
Claude Opus 5 · DeepSearchQA(900 prompts;单代理与多代理按协议区分),DeepSearchQA · High effort配置,F1 score 94.1%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF p.165, Figure 8.10.3.A; Opus 5 series labels。 查看成绩条件
Claude Opus 5 · DeepSearchQA(900 prompts;单代理与多代理按协议区分),DeepSearchQA · Xhigh effort配置,F1 score 94.6%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF p.165, Figure 8.10.3.A; Opus 5 series labels。 查看成绩条件
Claude Opus 5 · DeepSearchQA(900 prompts;单代理与多代理按协议区分),DeepSearchQA · Max effort配置,F1 score 95%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF p.165, Figure 8.10.3.A; Opus 5 series labels。 查看成绩条件
视觉转录(Claude Opus 5 图中明确标注):Mean F1: low 91.0%; medium 92.8%; high 94.1%; xhigh 94.6%; max 95.0%. Figure states a 980K-token budget; section describes a 1M budget without context compaction and search/fetch/programmatic tools.
附件 · System Card PDF p.165, Figure 8.10.3.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 · DeepSearchQA(900 prompts;单代理与多代理按协议区分),DeepSearchQA · Low effort配置,F1 score 91%(具体成绩公布时间未确认);Claude Opus 5 · DeepSearchQA(900 prompts;单代理与多代理按协议区分),DeepSearchQA · Medium effort配置,F1 score 92.8%(具体成绩公布时间未确认);Claude Opus 5 · DeepSearchQA(900 prompts;单代理与多代理按协议区分),DeepSearchQA · High effort配置,F1 score 94.1%(具体成绩公布时间未确认);Claude Opus 5 · DeepSearchQA(900 prompts;单代理与多代理按协议区分),DeepSearchQA · Xhigh effort配置,F1 score 94.6%(具体成绩公布时间未确认);Claude Opus 5 · DeepSearchQA(900 prompts;单代理与多代理按协议区分),DeepSearchQA · Max effort配置,F1 score 95%(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.165, Figure 8.10.3.A; Opus 5 series labels,https://www.anthropic.com/claude-opus-5-system-card#page=165。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5/ev-op5-card-deepsearchqa/
关联成绩与条件
Claude Opus 5 · DeepSearchQA 成绩与配置
指标与成绩
配置与评测条件
证据关系
F1 score91%原文 91% · 单位 %
公布 未确认
DeepSearchQA · Low effort
设置
900 multi-hop web-research prompts; web search, web fetch, and programmatic tool calling; adaptive thinking; figure states a 980K-token budget; section states a 1M budget and no context compaction. 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
DeepSearchQA; mean F1 across 900 multi-hop web-research questions.
条件
Explicit effort labels; figure budget 980K tokens; section describes web search, web fetch, programmatic tools, 1M token budget, no context compaction.
900 multi-hop web-research prompts; web search, web fetch, and programmatic tool calling; adaptive thinking; figure states a 980K-token budget; section states a 1M budget and no context compaction. 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
DeepSearchQA; mean F1 across 900 multi-hop web-research questions.
条件
Explicit effort labels; figure budget 980K tokens; section describes web search, web fetch, programmatic tools, 1M token budget, no context compaction.
900 multi-hop web-research prompts; web search, web fetch, and programmatic tool calling; adaptive thinking; figure states a 980K-token budget; section states a 1M budget and no context compaction. 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
DeepSearchQA; mean F1 across 900 multi-hop web-research questions.
条件
Explicit effort labels; figure budget 980K tokens; section describes web search, web fetch, programmatic tools, 1M token budget, no context compaction.
900 multi-hop web-research prompts; web search, web fetch, and programmatic tool calling; adaptive thinking; figure states a 980K-token budget; section states a 1M budget and no context compaction. 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
DeepSearchQA; mean F1 across 900 multi-hop web-research questions.
条件
Explicit effort labels; figure budget 980K tokens; section describes web search, web fetch, programmatic tools, 1M token budget, no context compaction.
900 multi-hop web-research prompts; web search, web fetch, and programmatic tool calling; adaptive thinking; figure states a 980K-token budget; section states a 1M budget and no context compaction. 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
DeepSearchQA; mean F1 across 900 multi-hop web-research questions.
条件
Explicit effort labels; figure budget 980K tokens; section describes web search, web fetch, programmatic tools, 1M token budget, no context compaction.
Claude Opus 5 · DeepSearchQA (900 prompts;单代理与多代理按协议区分) · Attachment evidence (ev-op5-card-deepsearchqa)
Official source for DeepSearchQA · 900 prompts;单代理与多代理按协议区分 in Claude Opus 5. See “Claude Opus 5 System Card” at System Card PDF p.165, Figure 8.10.3.A; Opus 5 series labels. Evidence ev-op5-card-deepsearchqa.
Claude Opus 5 · DeepSearchQA (900 prompts;单代理与多代理按协议区分), configuration DeepSearchQA · Low effort, F1 score 91% (exact score publication date unconfirmed). See “Claude Opus 5 System Card” at System Card PDF p.165, Figure 8.10.3.A; Opus 5 series labels. View score conditions
Claude Opus 5 · DeepSearchQA (900 prompts;单代理与多代理按协议区分), configuration DeepSearchQA · Medium effort, F1 score 92.8% (exact score publication date unconfirmed). See “Claude Opus 5 System Card” at System Card PDF p.165, Figure 8.10.3.A; Opus 5 series labels. View score conditions
Claude Opus 5 · DeepSearchQA (900 prompts;单代理与多代理按协议区分), configuration DeepSearchQA · High effort, F1 score 94.1% (exact score publication date unconfirmed). See “Claude Opus 5 System Card” at System Card PDF p.165, Figure 8.10.3.A; Opus 5 series labels. View score conditions
Claude Opus 5 · DeepSearchQA (900 prompts;单代理与多代理按协议区分), configuration DeepSearchQA · Xhigh effort, F1 score 94.6% (exact score publication date unconfirmed). See “Claude Opus 5 System Card” at System Card PDF p.165, Figure 8.10.3.A; Opus 5 series labels. View score conditions
Claude Opus 5 · DeepSearchQA (900 prompts;单代理与多代理按协议区分), configuration DeepSearchQA · Max effort, F1 score 95% (exact score publication date unconfirmed). See “Claude Opus 5 System Card” at System Card PDF p.165, Figure 8.10.3.A; Opus 5 series labels. View score conditions
视觉转录(Claude Opus 5 图中明确标注):Mean F1: low 91.0%; medium 92.8%; high 94.1%; xhigh 94.6%; max 95.0%. Figure states a 980K-token budget; section describes a 1M budget without context compaction and search/fetch/programmatic tools.
Attachment · System Card PDF p.165, Figure 8.10.3.A; Opus 5 series labels
Material version
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.
Version published
Unconfirmed
Disclosure date
Unconfirmed · Launch or later disclosure unconfirmed
Collected
Historical basis
No reliable historical version evidence available
Citation text
Claude Opus 5 · DeepSearchQA (900 prompts;单代理与多代理按协议区分), configuration DeepSearchQA · Low effort, F1 score 91% (exact score publication date unconfirmed); Claude Opus 5 · DeepSearchQA (900 prompts;单代理与多代理按协议区分), configuration DeepSearchQA · Medium effort, F1 score 92.8% (exact score publication date unconfirmed); Claude Opus 5 · DeepSearchQA (900 prompts;单代理与多代理按协议区分), configuration DeepSearchQA · High effort, F1 score 94.1% (exact score publication date unconfirmed); Claude Opus 5 · DeepSearchQA (900 prompts;单代理与多代理按协议区分), configuration DeepSearchQA · Xhigh effort, F1 score 94.6% (exact score publication date unconfirmed); Claude Opus 5 · DeepSearchQA (900 prompts;单代理与多代理按协议区分), configuration DeepSearchQA · Max effort, F1 score 95% (exact score publication date unconfirmed). Official source: Claude Opus 5 System Card (Attachment, 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.165, Figure 8.10.3.A; Opus 5 series labels, https://www.anthropic.com/claude-opus-5-system-card#page=165. Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5/ev-op5-card-deepsearchqa/?lang=en
Related scores and conditions
Claude Opus 5 · DeepSearchQA scores and configurations
Metric and score
Configuration and evaluation conditions
Evidence relation
F1 score91%Reported 91% · Unit %
Published Unconfirmed
DeepSearchQA · Low effort
Settings
900 multi-hop web-research prompts; web search, web fetch, and programmatic tool calling; adaptive thinking; figure states a 980K-token budget; section states a 1M budget and no context compaction. Explicit adaptive-thinking effort: low.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.
Tools
Tools allowed
Reasoning budget
low
Framework
not recorded
Protocol
DeepSearchQA; mean F1 across 900 multi-hop web-research questions.
Conditions
Explicit effort labels; figure budget 980K tokens; section describes web search, web fetch, programmatic tools, 1M token budget, no context compaction.
900 multi-hop web-research prompts; web search, web fetch, and programmatic tool calling; adaptive thinking; figure states a 980K-token budget; section states a 1M budget and no context compaction. Explicit adaptive-thinking effort: medium.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.
Tools
Tools allowed
Reasoning budget
medium
Framework
not recorded
Protocol
DeepSearchQA; mean F1 across 900 multi-hop web-research questions.
Conditions
Explicit effort labels; figure budget 980K tokens; section describes web search, web fetch, programmatic tools, 1M token budget, no context compaction.
900 multi-hop web-research prompts; web search, web fetch, and programmatic tool calling; adaptive thinking; figure states a 980K-token budget; section states a 1M budget and no context compaction. Explicit adaptive-thinking effort: high.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.
Tools
Tools allowed
Reasoning budget
high
Framework
not recorded
Protocol
DeepSearchQA; mean F1 across 900 multi-hop web-research questions.
Conditions
Explicit effort labels; figure budget 980K tokens; section describes web search, web fetch, programmatic tools, 1M token budget, no context compaction.
900 multi-hop web-research prompts; web search, web fetch, and programmatic tool calling; adaptive thinking; figure states a 980K-token budget; section states a 1M budget and no context compaction. Explicit adaptive-thinking effort: xhigh.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.
Tools
Tools allowed
Reasoning budget
xhigh
Framework
not recorded
Protocol
DeepSearchQA; mean F1 across 900 multi-hop web-research questions.
Conditions
Explicit effort labels; figure budget 980K tokens; section describes web search, web fetch, programmatic tools, 1M token budget, no context compaction.
900 multi-hop web-research prompts; web search, web fetch, and programmatic tool calling; adaptive thinking; figure states a 980K-token budget; section states a 1M budget and no context compaction. Explicit adaptive-thinking effort: max.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.
Tools
Tools allowed
Reasoning budget
max
Framework
not recorded
Protocol
DeepSearchQA; mean F1 across 900 multi-hop web-research questions.
Conditions
Explicit effort labels; figure budget 980K tokens; section describes web search, web fetch, programmatic tools, 1M token budget, no context compaction.