Claude Opus 5 · Humanity's Last Exam(2,500-question benchmark) · 附件证据(ev-op5-card-hle-headline)

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.152, Table 8.1.A; p.160, §8.10.1。证据 ev-op5-card-hle-headline。

原文与定位

Claude Opus 5 · Humanity's Last Exam(2,500-question benchmark),HLE · thinking auto, no tools配置,Accuracy 56.3%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF p.152, Table 8.1.A; p.160, §8.10.1。 查看成绩条件

Claude Opus 5 · Humanity's Last Exam(2,500-question benchmark),HLE · thinking auto, with tools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.152, Table 8.1.A; p.160, §8.10.1。 查看成绩条件

Table 8.1.A: HLE 56.3% without tools and 64.7% with tools. Section 8.10.1 states thinking=auto, a 1M total-token cap across contexts, no context compaction, and Opus 4.6 grading.
官方材料
Claude Opus 5 System Card · PDF 第 160 页
定位
附件 · System Card PDF p.152, Table 8.1.A; p.160, §8.10.1
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 · thinking auto, no tools配置,Accuracy 56.3%(具体成绩公布时间未确认);Claude Opus 5 · Humanity's Last Exam(2,500-question benchmark),HLE · thinking auto, with tools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.152, Table 8.1.A; p.160, §8.10.1,https://www.anthropic.com/claude-opus-5-system-card#page=160。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5/ev-op5-card-hle-headline/

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
Accuracy56.3%原文 56.3% · 单位 %
公布 未确认
HLE · thinking auto, no tools
设置
Reasoning-only configuration; thinking=auto; 1M total-token cap across contexts; no context compaction; Opus 4.6 model grader.
未知项
The headline result does not identify a low-to-max effort setting.
工具
禁止工具
推理预算
max
框架
未记录
协议
Humanity’s Last Exam; reasoning-only, without tools.
条件
56.3%; thinking=auto; 1M total-token cap across contexts; no context compaction; Opus 4.6 grader. This headline run is distinct from explicit low-to-max effort charts.

直接支持该成绩

在排名中查看此成绩
Accuracy64.7%原文 64.7% · 单位 %
公布 未确认
HLE · thinking auto, with tools
设置
Web search, web fetch, programmatic tool calling, and code execution; thinking=auto; 1M total-token cap across contexts; no context compaction; Opus 4.6 grader; HLE-specific URL blocklist and transcript contamination review.
未知项
The headline result does not identify a low-to-max effort setting.
工具
允许工具
推理预算
max
框架
未记录
协议
Humanity’s Last Exam; web search, web fetch, programmatic tool calling, and code execution.
条件
64.7%; thinking=auto; 1M total-token cap across contexts; no context compaction; Opus 4.6 grader; blocklist and transcript contamination review. Distinct from explicit effort charts.

直接支持该成绩

在排名中查看此成绩