Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark) · 附件证据(ev-h55-card-hle)

Claude Haiku 5.5 的 Humanity's Last Exam · 2,500-question benchmark 官方出处。见《Claude Haiku 5.5 System Card》System Card PDF pp.111, 118-120, Table 8.1.A and Figures 8.8.1.A-B。证据 ev-h55-card-hle。

原文与定位

Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE without tools / max配置,Accuracy 45.9%(具体成绩公布时间未确认)。见《Claude Haiku 5.5 System Card》System Card PDF pp.111, 118-120, Table 8.1.A and Figures 8.8.1.A-B。 查看成绩条件

Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE with tools / low配置,Accuracy 38.6%(具体成绩公布时间未确认)。见《Claude Haiku 5.5 System Card》System Card PDF pp.111, 118-120, Table 8.1.A and Figures 8.8.1.A-B。 查看成绩条件

Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE with tools / medium配置,Accuracy 45%(具体成绩公布时间未确认)。见《Claude Haiku 5.5 System Card》System Card PDF pp.111, 118-120, Table 8.1.A and Figures 8.8.1.A-B。 查看成绩条件

Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE with tools / high配置,Accuracy 50.1%(具体成绩公布时间未确认)。见《Claude Haiku 5.5 System Card》System Card PDF pp.111, 118-120, Table 8.1.A and Figures 8.8.1.A-B。 查看成绩条件

Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE with tools / xhigh配置,Accuracy 54.8%(具体成绩公布时间未确认)。见《Claude Haiku 5.5 System Card》System Card PDF pp.111, 118-120, Table 8.1.A and Figures 8.8.1.A-B。 查看成绩条件

Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE with tools / max配置,Accuracy 57.4%(具体成绩公布时间未确认)。见《Claude Haiku 5.5 System Card》System Card PDF pp.111, 118-120, Table 8.1.A and Figures 8.8.1.A-B。 查看成绩条件

Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE without tools / low配置,Accuracy 30.9%(具体成绩公布时间未确认)。见《Claude Haiku 5.5 System Card》System Card PDF pp.111, 118-120, Table 8.1.A and Figures 8.8.1.A-B。 查看成绩条件

Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE without tools / medium配置,Accuracy 35.5%(具体成绩公布时间未确认)。见《Claude Haiku 5.5 System Card》System Card PDF pp.111, 118-120, Table 8.1.A and Figures 8.8.1.A-B。 查看成绩条件

Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE without tools / high配置,Accuracy 39.7%(具体成绩公布时间未确认)。见《Claude Haiku 5.5 System Card》System Card PDF pp.111, 118-120, Table 8.1.A and Figures 8.8.1.A-B。 查看成绩条件

Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE without tools / xhigh配置,Accuracy 44.1%(具体成绩公布时间未确认)。见《Claude Haiku 5.5 System Card》System Card PDF pp.111, 118-120, Table 8.1.A and Figures 8.8.1.A-B。 查看成绩条件

HLE scores are 45.9% without tools and 57.4% with tools at max; the figures label effort-level scores explicitly.
官方材料
Claude Haiku 5.5 System Card · PDF 第 120 页
定位
附件 · System Card PDF pp.111, 118-120, Table 8.1.A and Figures 8.8.1.A-B
材料版本
144 页 PDF/TXT:本地留存副本、current-haiku-5-5-system-card.txt;封面日期 2026-10-07;正文 pp.1-144 已全文核读,全部63个含图/向量图表页实际视觉检查(本轮补看53页,合并此前10页),无未读页或未查看图表页;此为 current 卡片,不作为首发日附件证据。
版本公布
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 Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE without tools / max配置,Accuracy 45.9%(具体成绩公布时间未确认);Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE with tools / low配置,Accuracy 38.6%(具体成绩公布时间未确认);Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE with tools / medium配置,Accuracy 45%(具体成绩公布时间未确认);Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE with tools / high配置,Accuracy 50.1%(具体成绩公布时间未确认);Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE with tools / xhigh配置,Accuracy 54.8%(具体成绩公布时间未确认);Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE with tools / max配置,Accuracy 57.4%(具体成绩公布时间未确认);Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE without tools / low配置,Accuracy 30.9%(具体成绩公布时间未确认);Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE without tools / medium配置,Accuracy 35.5%(具体成绩公布时间未确认);Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE without tools / high配置,Accuracy 39.7%(具体成绩公布时间未确认);Claude Haiku 5.5 · Humanity's Last Exam(2,500-question benchmark),HLE without tools / xhigh配置,Accuracy 44.1%(具体成绩公布时间未确认)。官方出处 Claude Haiku 5.5 System Card(附件,144 页 PDF/TXT:本地留存副本、current-haiku-5-5-system-card.txt;封面日期 2026-10-07;正文 pp.1-144 已全文核读,全部63个含图/向量图表页实际视觉检查(本轮补看53页,合并此前10页),无未读页或未查看图表页;此为 current 卡片,不作为首发日附件证据。)System Card PDF pp.111, 118-120, Table 8.1.A and Figures 8.8.1.A-B,https://www.anthropic.com/claude-haiku-5-5-system-card#page=120。Benchlog https://benchlog.lekshome.cc/evidence/claude-haiku-5-5/ev-h55-card-hle/

关联成绩与条件

Claude Haiku 5.5 · Humanity's Last Exam 成绩与配置
指标与成绩配置与评测条件证据关系
Accuracy45.9%原文 45.9% no tools · 单位 %
公布 未确认
HLE without tools / max
设置
Thinking auto; max effort; no tools; 980k-token task budget; no context compaction.
未知项
Per-effort trial count is not stated in the chart caption where applicable.
工具
禁止工具
推理预算
max
框架
未记录
协议
Humanity’s Last Exam; no tools; 980k-token task budget; no context compaction.
条件
Max effort; this is the no-tools main-table result. The card’s effort figure also labels the same 45.9% max point.

直接支持该成绩

在排名中查看此成绩
Accuracy38.6%原文 38.6% · 单位 %
公布 未确认
HLE with tools / low
设置
Thinking auto; low effort; web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget; no context compaction; Opus 4.6 grader.
未知项
Per-effort trial count is not stated in the chart caption where applicable.
工具
允许工具
推理预算
low
框架
未记录
协议
Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
条件
Low effort; no context compaction; Opus 4.6 grader; point read from the labeled figure.

直接支持该成绩

在排名中查看此成绩
Accuracy45%原文 45.0% · 单位 %
公布 未确认
HLE with tools / medium
设置
Thinking auto; medium effort; web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget; no context compaction; Opus 4.6 grader.
未知项
Per-effort trial count is not stated in the chart caption where applicable.
工具
允许工具
推理预算
medium
框架
未记录
协议
Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
条件
Medium effort; no context compaction; Opus 4.6 grader; point read from the labeled figure.

直接支持该成绩

在排名中查看此成绩
Accuracy50.1%原文 50.1% · 单位 %
公布 未确认
HLE with tools / high
设置
Thinking auto; high effort; web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget; no context compaction; Opus 4.6 grader.
未知项
Per-effort trial count is not stated in the chart caption where applicable.
工具
允许工具
推理预算
high
框架
未记录
协议
Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
条件
High effort; no context compaction; Opus 4.6 grader; point read from the labeled figure.

直接支持该成绩

在排名中查看此成绩
Accuracy54.8%原文 54.8% · 单位 %
公布 未确认
HLE with tools / xhigh
设置
Thinking auto; xhigh effort; web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget; no context compaction; Opus 4.6 grader.
未知项
Per-effort trial count is not stated in the chart caption where applicable.
工具
允许工具
推理预算
xhigh
框架
未记录
协议
Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
条件
Xhigh effort; no context compaction; Opus 4.6 grader; point read from the labeled figure.

直接支持该成绩

在排名中查看此成绩
Accuracy57.4%原文 57.4% · 单位 %
公布 未确认
HLE with tools / max
设置
Thinking auto; max effort; web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget; no context compaction; Opus 4.6 grader.
未知项
Per-effort trial count is not stated in the chart caption where applicable.
工具
允许工具
推理预算
max
框架
未记录
协议
Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
条件
Max effort; no context compaction; Opus 4.6 grader; point read from the labeled figure.

直接支持该成绩

在排名中查看此成绩
Accuracy30.9%原文 30.9% · 单位 %
公布 未确认
HLE without tools / low
设置
Thinking auto; low effort; no tools; 980k-token task budget; no context compaction.
未知项
Per-effort trial count is not stated in the chart caption where applicable.
工具
禁止工具
推理预算
low
框架
未记录
协议
Humanity’s Last Exam; no tools; 980k-token task budget.
条件
Low effort; no context compaction; point read from the labeled figure.

直接支持该成绩

在排名中查看此成绩
Accuracy35.5%原文 35.5% · 单位 %
公布 未确认
HLE without tools / medium
设置
Thinking auto; medium effort; no tools; 980k-token task budget; no context compaction.
未知项
Per-effort trial count is not stated in the chart caption where applicable.
工具
禁止工具
推理预算
medium
框架
未记录
协议
Humanity’s Last Exam; no tools; 980k-token task budget.
条件
Medium effort; no context compaction; point read from the labeled figure.

直接支持该成绩

在排名中查看此成绩
Accuracy39.7%原文 39.7% · 单位 %
公布 未确认
HLE without tools / high
设置
Thinking auto; high effort; no tools; 980k-token task budget; no context compaction.
未知项
Per-effort trial count is not stated in the chart caption where applicable.
工具
禁止工具
推理预算
high
框架
未记录
协议
Humanity’s Last Exam; no tools; 980k-token task budget.
条件
High effort; no context compaction; point read from the labeled figure.

直接支持该成绩

在排名中查看此成绩
Accuracy44.1%原文 44.1% · 单位 %
公布 未确认
HLE without tools / xhigh
设置
Thinking auto; xhigh effort; no tools; 980k-token task budget; no context compaction.
未知项
Per-effort trial count is not stated in the chart caption where applicable.
工具
禁止工具
推理预算
xhigh
框架
未记录
协议
Humanity’s Last Exam; no tools; 980k-token task budget.
条件
Xhigh effort; no context compaction; point read from the labeled figure.

直接支持该成绩

在排名中查看此成绩