Claude Opus 5 · Humanity's Last Exam(2,500-question benchmark) · 附件证据(ev-op5-card-hle-tools-sweep)
Claude Opus 5 的 Humanity's Last Exam · 2,500-question benchmark 官方出处。见《Claude Opus 5 System Card》System Card PDF p.161, Figure 8.10.1.A; Opus 5 series labels。证据 ev-op5-card-hle-tools-sweep。
Claude Opus 5 · Humanity's Last Exam(2,500-question benchmark),HLE effort sweep · with tools · Low effort配置,Accuracy 56.1%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF p.161, Figure 8.10.1.A; Opus 5 series labels。 查看成绩条件
Claude Opus 5 · Humanity's Last Exam(2,500-question benchmark),HLE effort sweep · with tools · Medium effort配置,Accuracy 61.3%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF p.161, Figure 8.10.1.A; Opus 5 series labels。 查看成绩条件
Claude Opus 5 · Humanity's Last Exam(2,500-question benchmark),HLE effort sweep · with tools · High effort配置,Accuracy 63.2%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF p.161, Figure 8.10.1.A; Opus 5 series labels。 查看成绩条件
Claude Opus 5 · Humanity's Last Exam(2,500-question benchmark),HLE effort sweep · with tools · Xhigh effort配置,Accuracy 64.8%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF p.161, Figure 8.10.1.A; Opus 5 series labels。 查看成绩条件
Claude Opus 5 · Humanity's Last Exam(2,500-question benchmark),HLE effort sweep · with tools · Max effort配置,Accuracy 64.7%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF p.161, Figure 8.10.1.A; Opus 5 series labels。 查看成绩条件
视觉转录(Claude Opus 5 图中明确标注):With tools: low 56.1%; medium 61.3%; high 63.2%; xhigh 64.8%; max 64.7%.
附件 · System Card PDF p.161, Figure 8.10.1.A; Opus 5 series labels
材料版本
Current saved PDF/TXT: 本地留存副本 and current-opus-5-system-card.txt; cover dated 2026-07-24; p.2 changelog records an update on 2026-08-19; later revision date, if any, unknown.
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 Opus 5 · Humanity's Last Exam(2,500-question benchmark),HLE effort sweep · with tools · Low effort配置,Accuracy 56.1%(具体成绩公布时间未确认);Claude Opus 5 · Humanity's Last Exam(2,500-question benchmark),HLE effort sweep · with tools · Medium effort配置,Accuracy 61.3%(具体成绩公布时间未确认);Claude Opus 5 · Humanity's Last Exam(2,500-question benchmark),HLE effort sweep · with tools · High effort配置,Accuracy 63.2%(具体成绩公布时间未确认);Claude Opus 5 · Humanity's Last Exam(2,500-question benchmark),HLE effort sweep · with tools · Xhigh effort配置,Accuracy 64.8%(具体成绩公布时间未确认);Claude Opus 5 · Humanity's Last Exam(2,500-question benchmark),HLE effort sweep · with tools · Max effort配置,Accuracy 64.7%(具体成绩公布时间未确认)。官方出处 Claude Opus 5 System Card(附件,Current saved PDF/TXT: 本地留存副本 and current-opus-5-system-card.txt; cover dated 2026-07-24; p.2 changelog records an update on 2026-08-19; later revision date, if any, unknown.)System Card PDF p.161, Figure 8.10.1.A; Opus 5 series labels,https://www.anthropic.com/claude-opus-5-system-card#page=161。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5/ev-op5-card-hle-tools-sweep/
关联成绩与条件
Claude Opus 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
Accuracy56.1%原文 56.1% · 单位 %
公布 未确认
HLE effort sweep · with tools · Low effort
设置
Tools enabled; explicit figure-labeled effort scaling; billed API cost reported. This is separate from the headline thinking=auto run. Explicit adaptive-thinking effort: low.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
工具
允许工具
推理预算
low
框架
未记录
协议
HLE effort-scaling figure; with tools.
条件
Explicit effort labels; billed API actuals; separate from the headline thinking=auto result; figure does not state a token cap or context-compaction setting.
Tools enabled; explicit figure-labeled effort scaling; billed API cost reported. This is separate from the headline thinking=auto run. Explicit adaptive-thinking effort: medium.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
工具
允许工具
推理预算
medium
框架
未记录
协议
HLE effort-scaling figure; with tools.
条件
Explicit effort labels; billed API actuals; separate from the headline thinking=auto result; figure does not state a token cap or context-compaction setting.
Tools enabled; explicit figure-labeled effort scaling; billed API cost reported. This is separate from the headline thinking=auto run. Explicit adaptive-thinking effort: high.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
工具
允许工具
推理预算
high
框架
未记录
协议
HLE effort-scaling figure; with tools.
条件
Explicit effort labels; billed API actuals; separate from the headline thinking=auto result; figure does not state a token cap or context-compaction setting.
Tools enabled; explicit figure-labeled effort scaling; billed API cost reported. This is separate from the headline thinking=auto run. Explicit adaptive-thinking effort: xhigh.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
工具
允许工具
推理预算
xhigh
框架
未记录
协议
HLE effort-scaling figure; with tools.
条件
Explicit effort labels; billed API actuals; separate from the headline thinking=auto result; figure does not state a token cap or context-compaction setting.
Tools enabled; explicit figure-labeled effort scaling; billed API cost reported. This is separate from the headline thinking=auto run. Explicit adaptive-thinking effort: max.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
工具
允许工具
推理预算
max
框架
未记录
协议
HLE effort-scaling figure; with tools.
条件
Explicit effort labels; billed API actuals; separate from the headline thinking=auto result; figure does not state a token cap or context-compaction setting.
Claude Opus 5 · Humanity's Last Exam (2,500-question benchmark) · Attachment evidence (ev-op5-card-hle-tools-sweep)
Official source for Humanity's Last Exam · 2,500-question benchmark in Claude Opus 5. See “Claude Opus 5 System Card” at System Card PDF p.161, Figure 8.10.1.A; Opus 5 series labels. Evidence ev-op5-card-hle-tools-sweep.
Claude Opus 5 · Humanity's Last Exam (2,500-question benchmark), configuration HLE effort sweep · with tools · Low effort, Accuracy 56.1% (exact score publication date unconfirmed). See “Claude Opus 5 System Card” at System Card PDF p.161, Figure 8.10.1.A; Opus 5 series labels. View score conditions
Claude Opus 5 · Humanity's Last Exam (2,500-question benchmark), configuration HLE effort sweep · with tools · Medium effort, Accuracy 61.3% (exact score publication date unconfirmed). See “Claude Opus 5 System Card” at System Card PDF p.161, Figure 8.10.1.A; Opus 5 series labels. View score conditions
Claude Opus 5 · Humanity's Last Exam (2,500-question benchmark), configuration HLE effort sweep · with tools · High effort, Accuracy 63.2% (exact score publication date unconfirmed). See “Claude Opus 5 System Card” at System Card PDF p.161, Figure 8.10.1.A; Opus 5 series labels. View score conditions
Claude Opus 5 · Humanity's Last Exam (2,500-question benchmark), configuration HLE effort sweep · with tools · Xhigh effort, Accuracy 64.8% (exact score publication date unconfirmed). See “Claude Opus 5 System Card” at System Card PDF p.161, Figure 8.10.1.A; Opus 5 series labels. View score conditions
Claude Opus 5 · Humanity's Last Exam (2,500-question benchmark), configuration HLE effort sweep · with tools · Max effort, Accuracy 64.7% (exact score publication date unconfirmed). See “Claude Opus 5 System Card” at System Card PDF p.161, Figure 8.10.1.A; Opus 5 series labels. View score conditions
视觉转录(Claude Opus 5 图中明确标注):With tools: low 56.1%; medium 61.3%; high 63.2%; xhigh 64.8%; max 64.7%.
Attachment · System Card PDF p.161, Figure 8.10.1.A; Opus 5 series labels
Material version
Current saved PDF/TXT: 本地留存副本 and current-opus-5-system-card.txt; cover dated 2026-07-24; p.2 changelog records an update on 2026-08-19; later revision date, if any, unknown.
Version published
Unconfirmed
Disclosure date
Unconfirmed · Launch or later disclosure unconfirmed
Collected
Historical basis
No reliable historical version evidence available
Citation text
Claude Opus 5 · Humanity's Last Exam (2,500-question benchmark), configuration HLE effort sweep · with tools · Low effort, Accuracy 56.1% (exact score publication date unconfirmed); Claude Opus 5 · Humanity's Last Exam (2,500-question benchmark), configuration HLE effort sweep · with tools · Medium effort, Accuracy 61.3% (exact score publication date unconfirmed); Claude Opus 5 · Humanity's Last Exam (2,500-question benchmark), configuration HLE effort sweep · with tools · High effort, Accuracy 63.2% (exact score publication date unconfirmed); Claude Opus 5 · Humanity's Last Exam (2,500-question benchmark), configuration HLE effort sweep · with tools · Xhigh effort, Accuracy 64.8% (exact score publication date unconfirmed); Claude Opus 5 · Humanity's Last Exam (2,500-question benchmark), configuration HLE effort sweep · with tools · Max effort, Accuracy 64.7% (exact score publication date unconfirmed). Official source: Claude Opus 5 System Card (Attachment, Current saved PDF/TXT: 本地留存副本 and current-opus-5-system-card.txt; cover dated 2026-07-24; p.2 changelog records an update on 2026-08-19; later revision date, if any, unknown.), System Card PDF p.161, Figure 8.10.1.A; Opus 5 series labels, https://www.anthropic.com/claude-opus-5-system-card#page=161. Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5/ev-op5-card-hle-tools-sweep/?lang=en
Related scores and conditions
Claude Opus 5 · Humanity's Last Exam scores and configurations
Metric and score
Configuration and evaluation conditions
Evidence relation
Accuracy56.1%Reported 56.1% · Unit %
Published Unconfirmed
HLE effort sweep · with tools · Low effort
Settings
Tools enabled; explicit figure-labeled effort scaling; billed API cost reported. This is separate from the headline thinking=auto run. Explicit adaptive-thinking effort: low.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.
Tools
Tools allowed
Reasoning budget
low
Framework
not recorded
Protocol
HLE effort-scaling figure; with tools.
Conditions
Explicit effort labels; billed API actuals; separate from the headline thinking=auto result; figure does not state a token cap or context-compaction setting.
Tools enabled; explicit figure-labeled effort scaling; billed API cost reported. This is separate from the headline thinking=auto run. Explicit adaptive-thinking effort: medium.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.
Tools
Tools allowed
Reasoning budget
medium
Framework
not recorded
Protocol
HLE effort-scaling figure; with tools.
Conditions
Explicit effort labels; billed API actuals; separate from the headline thinking=auto result; figure does not state a token cap or context-compaction setting.
Tools enabled; explicit figure-labeled effort scaling; billed API cost reported. This is separate from the headline thinking=auto run. Explicit adaptive-thinking effort: high.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.
Tools
Tools allowed
Reasoning budget
high
Framework
not recorded
Protocol
HLE effort-scaling figure; with tools.
Conditions
Explicit effort labels; billed API actuals; separate from the headline thinking=auto result; figure does not state a token cap or context-compaction setting.
Tools enabled; explicit figure-labeled effort scaling; billed API cost reported. This is separate from the headline thinking=auto run. Explicit adaptive-thinking effort: xhigh.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.
Tools
Tools allowed
Reasoning budget
xhigh
Framework
not recorded
Protocol
HLE effort-scaling figure; with tools.
Conditions
Explicit effort labels; billed API actuals; separate from the headline thinking=auto result; figure does not state a token cap or context-compaction setting.
Tools enabled; explicit figure-labeled effort scaling; billed API cost reported. This is separate from the headline thinking=auto run. Explicit adaptive-thinking effort: max.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.
Tools
Tools allowed
Reasoning budget
max
Framework
not recorded
Protocol
HLE effort-scaling figure; with tools.
Conditions
Explicit effort labels; billed API actuals; separate from the headline thinking=auto result; figure does not state a token cap or context-compaction setting.