Claude Sonnet 4.6 · BrowseComp(1,266 题;单代理与多代理按协议区分) 74.01% · 附件证据(ev46-browsecomp-current)

Claude Sonnet 4.6 的 BrowseComp · 1,266 题;单代理与多代理按协议区分 官方出处。No thinking, max effort · 74.01%。见《Claude Sonnet 4.6 System Card》§2.20.1.1 and Figure 2.20.1.1.A, PDF p.44。证据 ev46-browsecomp-current。

原文与定位

Claude Sonnet 4.6 · BrowseComp(1,266 题;单代理与多代理按协议区分),No thinking, max effort配置,Accuracy 74.01%(成绩公布 2026-03-06)。见《Claude Sonnet 4.6 System Card》§2.20.1.1 and Figure 2.20.1.1.A, PDF p.44。 查看成绩条件

Claude Sonnet 4.6 achieved 74.01% on BrowseComp, placing it above Claude Opus 4.5 and well ahead of the previous Sonnet model.
官方材料
Claude Sonnet 4.6 System Card · PDF 第 44 页
定位
附件 · §2.20.1.1 and Figure 2.20.1.1.A, PDF p.44
材料版本
PDF with changelog dated 2026-03-06; 135 pages; collected 2026-11-10
版本公布
未确认
披露时间
· 后补披露
采集时间
历史依据
暂无可靠历史版本依据
引用文本

Claude Sonnet 4.6 · BrowseComp(1,266 题;单代理与多代理按协议区分),No thinking, max effort配置,Accuracy 74.01%(成绩公布 2026-03-06)。官方出处 Claude Sonnet 4.6 System Card(附件,PDF with changelog dated 2026-03-06; 135 pages; collected 2026-11-10)§2.20.1.1 and Figure 2.20.1.1.A, PDF p.44,https://www.anthropic.com/claude-sonnet-4-6-system-card#page=44。Benchlog https://benchlog.lekshome.cc/evidence/claude-sonnet-4-6/ev46-browsecomp-current/

关联成绩与条件

Claude Sonnet 4.6 · BrowseComp 成绩与配置
指标与成绩配置与评测条件证据关系
Accuracy74.01%原文 74.01% · 单位 %
公布

更正记录 · 替代 74.72%。System Card changelog dated 2026-03-06 states that an improved cheating-detection pipeline flagged nine additional unintended solutions; the best-scoring single-agent configuration was re-verified, not rerun.

No thinking, max effort
设置
Thinking disabled; max effort.
未知项
Sampling settings are not specified in every evaluation.
工具
允许工具
推理预算
max
框架
未记录
协议
BrowseComp single-agent best configuration, 1,266 questions.
条件
Web search, web fetch, programmatic tool calling, context compaction triggered at 50K tokens, 10M total-token limit, max reasoning effort and no thinking.

直接支持该成绩

在排名中查看此成绩