Single agent; web search/fetch; programmatic tool calling; context compaction at 50K; 10M total-token limit; max reasoning effort; thinking disabled.
未知项
Trial count and exact sampling settings for the Opus 4.5 row are not stated.
工具
允许工具
推理预算
max
框架
未记录
协议
BrowseComp; single-agent; web search/fetch and programmatic tool calling.
条件
50K context compaction; 10M total-token limit; max reasoning effort with thinking disabled. Kept distinct from the custom BrowseComp-Plus evaluation. 来源主文最初发布日期为2026-02-05,但当前HTML修改于2026-10-14;没有与此数值匹配的首发图像历史字节,因此精确首次公布日未知。
Claude Opus 4.5 · BrowseComp · 1,266 题;单代理与多代理按协议区分 · Scores and configurations
Claude Opus 4.5 record for BrowseComp · 1,266 题;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 4.5 · BrowseComp scores and configurations
Metric and score
Configuration and evaluation conditions
Sources
Accuracy67.8%Reported 67.8% · Unit %
Published Unconfirmed
BrowseComp · comparison article · no thinking
Settings
Single agent; web search/fetch; programmatic tool calling; context compaction at 50K; 10M total-token limit; max reasoning effort; thinking disabled.
Unknowns
Trial count and exact sampling settings for the Opus 4.5 row are not stated.
Tools
Tools allowed
Reasoning budget
max
Framework
not recorded
Protocol
BrowseComp; single-agent; web search/fetch and programmatic tool calling.
Conditions
50K context compaction; 10M total-token limit; max reasoning effort with thinking disabled. Kept distinct from the custom BrowseComp-Plus evaluation. 来源主文最初发布日期为2026-02-05,但当前HTML修改于2026-10-14;没有与此数值匹配的首发图像历史字节,因此精确首次公布日未知。