Claude Opus 4.7 · Humanity's Last Exam(2,500-question benchmark) · 附件证据(ev-op47-card-hle-headline)
Claude Opus 4.7 的 Humanity's Last Exam · 2,500-question benchmark 官方出处。见《Claude Opus 4.7 System Card》§8.8.1 and Figure 8.8.1.A, PDF pp.196-197。证据 ev-op47-card-hle-headline。
Claude Opus 4.7 · Humanity's Last Exam(2,500-question benchmark),HLE 无工具配置,Accuracy 46.9%(具体成绩公布时间未确认)。见《Claude Opus 4.7 System Card》§8.8.1 and Figure 8.8.1.A, PDF pp.196-197。 查看成绩条件
Claude Opus 4.7 · Humanity's Last Exam(2,500-question benchmark),HLE 有工具配置,Accuracy 54.7%(具体成绩公布时间未确认)。见《Claude Opus 4.7 System Card》§8.8.1 and Figure 8.8.1.A, PDF pp.196-197。 查看成绩条件
Humanity’s Last Exam comprises 2,500 questions. Opus 4.7 scored 46.9% without tools and 54.7% with tools at max reasoning effort. Each headline result uses the §8.1 standard five-trial average unless otherwise stated.
Current saved PDF/TXT: 本地留存副本 and current-opus-4-7-system-card.txt; 232 PDF pages; metadata created/modified 2026-04-16 22:11:48 China Standard Time. Full current-card review completed 2026-11-16; this file is not established as launch-day bytes.
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 4.7 · Humanity's Last Exam(2,500-question benchmark),HLE 无工具配置,Accuracy 46.9%(具体成绩公布时间未确认);Claude Opus 4.7 · Humanity's Last Exam(2,500-question benchmark),HLE 有工具配置,Accuracy 54.7%(具体成绩公布时间未确认)。官方出处 Claude Opus 4.7 System Card(附件,Current saved PDF/TXT: 本地留存副本 and current-opus-4-7-system-card.txt; 232 PDF pages; metadata created/modified 2026-04-16 22:11:48 China Standard Time. Full current-card review completed 2026-11-16; this file is not established as launch-day bytes.)§8.8.1 and Figure 8.8.1.A, PDF pp.196-197,https://www.anthropic.com/claude-opus-4-7-system-card#page=196。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-4-7/ev-op47-card-hle-headline/
关联成绩与条件
Claude Opus 4.7 · 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
Accuracy46.9%原文 46.9% · 单位 %
公布 未确认
HLE 无工具
设置
HLE reasoning-only, no tools; thinking auto; max reasoning effort; total tokens across contexts capped at 1M; no context compaction; Claude Opus 4.6 grader; standard five-trial average applies to the headline result.
未知项
The card does not state a separate headline trial count; the §8.1 standard average of five trials applies.
工具
禁止工具
推理预算
max
框架
未记录
协议
HLE; no tools。
条件
2,500 questions; reasoning-only, no tools; thinking auto; max reasoning effort; total context tokens capped at 1M; no context compaction; Opus 4.6 grader; §8.1 five-trial average applies.
HLE with web search, web fetch, programmatic tool calling and code execution; thinking auto; max reasoning effort; total tokens across contexts capped at 1M; no context compaction; Claude Opus 4.6 grader; known HLE sources blocklisted and transcripts reviewed.
未知项
The card does not state a separate headline trial count; the §8.1 standard average of five trials applies. Single-run effort-chart points use distinct configs.
工具
允许工具
推理预算
max
框架
未记录
协议
HLE; with tools。
条件
2,500 questions; web search, web fetch, programmatic tool calling and code execution; thinking auto; max reasoning effort; 1M total-token cap; no context compaction; HLE source blocklist and Opus 4.6 transcript review; §8.1 five-trial average applies.
Claude Opus 4.7 · Humanity's Last Exam (2,500-question benchmark) · Attachment evidence (ev-op47-card-hle-headline)
Official source for Humanity's Last Exam · 2,500-question benchmark in Claude Opus 4.7. See “Claude Opus 4.7 System Card” at §8.8.1 and Figure 8.8.1.A, PDF pp.196-197. Evidence ev-op47-card-hle-headline.
Claude Opus 4.7 · Humanity's Last Exam (2,500-question benchmark), configuration HLE 无工具, Accuracy 46.9% (exact score publication date unconfirmed). See “Claude Opus 4.7 System Card” at §8.8.1 and Figure 8.8.1.A, PDF pp.196-197. View score conditions
Claude Opus 4.7 · Humanity's Last Exam (2,500-question benchmark), configuration HLE 有工具, Accuracy 54.7% (exact score publication date unconfirmed). See “Claude Opus 4.7 System Card” at §8.8.1 and Figure 8.8.1.A, PDF pp.196-197. View score conditions
Humanity’s Last Exam comprises 2,500 questions. Opus 4.7 scored 46.9% without tools and 54.7% with tools at max reasoning effort. Each headline result uses the §8.1 standard five-trial average unless otherwise stated.
Attachment · §8.8.1 and Figure 8.8.1.A, PDF pp.196-197
Material version
Current saved PDF/TXT: 本地留存副本 and current-opus-4-7-system-card.txt; 232 PDF pages; metadata created/modified 2026-04-16 22:11:48 China Standard Time. Full current-card review completed 2026-11-16; this file is not established as launch-day bytes.
Version published
Unconfirmed
Disclosure date
Unconfirmed · Launch or later disclosure unconfirmed
Collected
Historical basis
No reliable historical version evidence available
Citation text
Claude Opus 4.7 · Humanity's Last Exam (2,500-question benchmark), configuration HLE 无工具, Accuracy 46.9% (exact score publication date unconfirmed); Claude Opus 4.7 · Humanity's Last Exam (2,500-question benchmark), configuration HLE 有工具, Accuracy 54.7% (exact score publication date unconfirmed). Official source: Claude Opus 4.7 System Card (Attachment, Current saved PDF/TXT: 本地留存副本 and current-opus-4-7-system-card.txt; 232 PDF pages; metadata created/modified 2026-04-16 22:11:48 China Standard Time. Full current-card review completed 2026-11-16; this file is not established as launch-day bytes.), §8.8.1 and Figure 8.8.1.A, PDF pp.196-197, https://www.anthropic.com/claude-opus-4-7-system-card#page=196. Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-4-7/ev-op47-card-hle-headline/?lang=en
Related scores and conditions
Claude Opus 4.7 · Humanity's Last Exam scores and configurations
Metric and score
Configuration and evaluation conditions
Evidence relation
Accuracy46.9%Reported 46.9% · Unit %
Published Unconfirmed
HLE 无工具
Settings
HLE reasoning-only, no tools; thinking auto; max reasoning effort; total tokens across contexts capped at 1M; no context compaction; Claude Opus 4.6 grader; standard five-trial average applies to the headline result.
Unknowns
The card does not state a separate headline trial count; the §8.1 standard average of five trials applies.
Tools
Tools forbidden
Reasoning budget
max
Framework
not recorded
Protocol
HLE; no tools。
Conditions
2,500 questions; reasoning-only, no tools; thinking auto; max reasoning effort; total context tokens capped at 1M; no context compaction; Opus 4.6 grader; §8.1 five-trial average applies.
HLE with web search, web fetch, programmatic tool calling and code execution; thinking auto; max reasoning effort; total tokens across contexts capped at 1M; no context compaction; Claude Opus 4.6 grader; known HLE sources blocklisted and transcripts reviewed.
Unknowns
The card does not state a separate headline trial count; the §8.1 standard average of five trials applies. Single-run effort-chart points use distinct configs.
Tools
Tools allowed
Reasoning budget
max
Framework
not recorded
Protocol
HLE; with tools。
Conditions
2,500 questions; web search, web fetch, programmatic tool calling and code execution; thinking auto; max reasoning effort; 1M total-token cap; no context compaction; HLE source blocklist and Opus 4.6 transcript review; §8.1 five-trial average applies.