Home Model series Claude Opus Claude Opus 4.8 Claude Opus 4.8 · DeepSearchQA · 900 prompts;单代理与多代理按协议区分 · Scores and configurations Claude Opus 4.8 · DeepSearchQA · 900 prompts;单代理与多代理按协议区分 · Scores and configurations Claude Opus 4.8 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.
Scores and evaluation conditions Claude Opus 4.8 · DeepSearchQA scores and configurations Metric and score Configuration and evaluation conditions Sources F1 score 93.1% Reported 93.1% · Unit % Published Unconfirmed
DeepSearchQA single-agent Settings Web search、web fetch、programmatic tool calling;adaptive thinking 与 max effort;900 prompts,1M token budget,不使用 context compaction。 Unknowns none recorded Tools Tools allowed Reasoning budget max Framework not recorded Protocol DeepSearchQA, 900 prompts; web search/fetch and programmatic tool calling; 1M token budget without context compaction. Conditions Adaptive thinking and max effort. Table 8.10.3.B reports F1 93.1% (±1.4%), fully correct 84.8%, fully incorrect 3.9%, correct with excessive answers 4.3%. View this score in rankings
Benchmark versions and metrics Aliases DeepSearchQA、DeepSearchQA with multi-agents
F1 score · % · Higher is better Accuracy · % · Higher is better