Claude Sonnet 5 · BrowseComp(1,266 题;单代理与多代理按协议区分) · 附件证据(ev5-browsecomp-direct-card-chart)

Claude Sonnet 5 的 BrowseComp · 1,266 题;单代理与多代理按协议区分 官方出处。见《Claude Sonnet 5 System Card (145-page version directly linked by the announcement methodology correction)》§8.9.2 Figure 8.9.2.A, PDF p.123, orange Claude Sonnet 5 series printed labels。证据 ev5-browsecomp-direct-card-chart。

原文与定位

Claude Sonnet 5 · BrowseComp(1,266 题;单代理与多代理按协议区分),Standard configuration: adaptive thinking, max effort配置,Accuracy 84.7%(具体成绩公布时间未确认)。见《Claude Sonnet 5 System Card (145-page version directly linked by the announcement methodology correction)》§8.9.2 Figure 8.9.2.A, PDF p.123, orange Claude Sonnet 5 series printed labels。 查看成绩条件

Claude Sonnet 5 · BrowseComp(1,266 题;单代理与多代理按协议区分),BrowseComp max effort, 1M-token limit配置,Accuracy 79.3%(具体成绩公布时间未确认)。见《Claude Sonnet 5 System Card (145-page version directly linked by the announcement methodology correction)》§8.9.2 Figure 8.9.2.A, PDF p.123, orange Claude Sonnet 5 series printed labels。 查看成绩条件

Claude Sonnet 5 · BrowseComp(1,266 题;单代理与多代理按协议区分),BrowseComp max effort, 3M-token limit配置,Accuracy 82.9%(具体成绩公布时间未确认)。见《Claude Sonnet 5 System Card (145-page version directly linked by the announcement methodology correction)》§8.9.2 Figure 8.9.2.A, PDF p.123, orange Claude Sonnet 5 series printed labels。 查看成绩条件

1M token limit 79.3%; 3M token limit 82.9%; 10M token limit 84.7%
官方材料
Claude Sonnet 5 System Card (145-page version directly linked by the announcement methodology correction) · PDF 第 123 页
定位
附件 · §8.9.2 Figure 8.9.2.A, PDF p.123, orange Claude Sonnet 5 series printed labels
材料版本
145-page PDF with cover date June 30, 2026; no July 10 changelog or public Messages API reproduction footnote; current announcement links this version in its methodology correction. Cover date does not establish the collected file publication time.
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 · BrowseComp(1,266 题;单代理与多代理按协议区分),Standard configuration: adaptive thinking, max effort配置,Accuracy 84.7%(具体成绩公布时间未确认);Claude Sonnet 5 · BrowseComp(1,266 题;单代理与多代理按协议区分),BrowseComp max effort, 1M-token limit配置,Accuracy 79.3%(具体成绩公布时间未确认);Claude Sonnet 5 · BrowseComp(1,266 题;单代理与多代理按协议区分),BrowseComp max effort, 3M-token limit配置,Accuracy 82.9%(具体成绩公布时间未确认)。官方出处 Claude Sonnet 5 System Card (145-page version directly linked by the announcement methodology correction)(附件,145-page PDF with cover date June 30, 2026; no July 10 changelog or public Messages API reproduction footnote; current announcement links this version in its methodology correction. Cover date does not establish the collected file publication time.)§8.9.2 Figure 8.9.2.A, PDF p.123, orange Claude Sonnet 5 series printed labels,https://assets.claude.com/9e6a1044980d8c4ed85669faf9c2a8342e2e9f1e.pdf#page=123。Benchlog https://benchlog.lekshome.cc/evidence/claude-sonnet-5/ev5-browsecomp-direct-card-chart/

关联成绩与条件

Claude Sonnet 5 · BrowseComp 成绩与配置
指标与成绩配置与评测条件证据关系
Accuracy84.7%原文 84.7% · 单位 %
公布 未确认
Standard configuration: adaptive thinking, max effort
设置
Adaptive thinking at max effort; default temperature and top_p; five-trial averages unless otherwise stated.
未知项
Context-window size is evaluation-dependent; standard configuration is 1M tokens.
工具
允许工具
推理预算
max
框架
未记录
协议
BrowseComp with web search, web fetch, programmatic tool calling and code execution.
条件
Adaptive thinking, max effort, 10M token limit, 200K context compaction, evaluation blocklist. Original page chart was replaced after the source identified a simpler methodology; prior numeric value was not given and is not reconstructed.

直接支持该成绩

在排名中查看此成绩
Accuracy79.3%原文 79.3% · 单位 %
公布 未确认
BrowseComp max effort, 1M-token limit
设置
Adaptive thinking at max effort with web search, web fetch, programmatic tool calling, and code execution; 1M-token limit.
未知项
Whether context compaction was used at this token limit is not stated.
工具
允许工具
推理预算
max
框架
未记录
协议
BrowseComp Figure 8.9.2.A, test-time compute scaling at max effort with web search, web fetch, programmatic tool calling, and code execution.
条件
1M-token limit as labeled. The figure gives no exact per-point cost label.

直接支持该成绩

Accuracy82.9%原文 82.9% · 单位 %
公布 未确认
BrowseComp max effort, 3M-token limit
设置
Adaptive thinking at max effort with web search, web fetch, programmatic tool calling, and code execution; 3M-token limit; context compaction is reported as triggering at 200K tokens when extending beyond the 1M context window.
未知项
Sampling parameters are not stated.
工具
允许工具
推理预算
max
框架
未记录
协议
BrowseComp Figure 8.9.2.A, test-time compute scaling at max effort with web search, web fetch, programmatic tool calling, and code execution.
条件
3M-token limit as labeled; §8.9.2 reports context compaction triggered at 200K tokens to extend beyond the 1M context window. The figure gives no exact per-point cost label.

直接支持该成绩