900 prompts; web search, web fetch, programmatic tool calling; adaptive thinking, max effort; context compaction at 200K; up to 10M total tokens.
未知项
未另记
工具
允许工具
推理预算
max
框架
未记录
协议
DeepSearchQA; 900 prompts; single-agent; F1.
条件
Web search, web fetch, programmatic tool calling; adaptive thinking and max effort; 200K compaction trigger; up to 10M total tokens. Table 8.8.3.B reports ±1.8%.
Claude Opus 4.7 · DeepSearchQA · 900 prompts;单代理与多代理按协议区分 · Scores and configurations
Claude Opus 4.7 record for DeepSearchQA · 900 prompts;单代理与多代理按协议区分. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.
Claude Opus 4.7 · DeepSearchQA scores and configurations
Metric and score
Configuration and evaluation conditions
Sources
F1 score89.1%Reported 89.1% ±1.8% · Unit %
Published Unconfirmed
DeepSearchQA,single-agent
Settings
900 prompts; web search, web fetch, programmatic tool calling; adaptive thinking, max effort; context compaction at 200K; up to 10M total tokens.
Unknowns
none recorded
Tools
Tools allowed
Reasoning budget
max
Framework
not recorded
Protocol
DeepSearchQA; 900 prompts; single-agent; F1.
Conditions
Web search, web fetch, programmatic tool calling; adaptive thinking and max effort; 200K compaction trigger; up to 10M total tokens. Table 8.8.3.B reports ±1.8%.