Claude Opus 4.8 · Humanity's Last Exam(2,500-question benchmark),HLE 无工具配置,Accuracy 49.8%(具体成绩公布时间未确认)。见《Introducing Claude Opus 4.8》Humanity's Last Exam 行。 查看成绩条件
Claude Opus 4.8 · Humanity's Last Exam(2,500-question benchmark),HLE 有工具配置,Accuracy 57.9%(具体成绩公布时间未确认)。见《Introducing Claude Opus 4.8》Humanity's Last Exam 行。 查看成绩条件
Claude Opus 4.8 · Humanity's Last Exam(2,500-question benchmark),HLE 无工具配置,Accuracy 49.8%(具体成绩公布时间未确认);Claude Opus 4.8 · Humanity's Last Exam(2,500-question benchmark),HLE 有工具配置,Accuracy 57.9%(具体成绩公布时间未确认)。官方出处 Introducing Claude Opus 4.8(主文,官方发布页;本地保存 HTML/TXT 与主表 PNG:本地留存副本、本地留存副本、本地留存副本;原文发布日期 2026-05-28,当前修订时间未知)Humanity's Last Exam 行,https://www.anthropic.com/news/claude-opus-4-8#opus-48s-capabilities。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-4-8/ev-op48-hle/
关联成绩与条件
Claude Opus 4.8 · 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
Accuracy49.8%原文 49.8% · 单位 %
公布 未确认
HLE 无工具
设置
Humanity’s Last Exam; reasoning only, no tools; auto thinking and max effort; 1M total-token cap; no context compaction. Some items exceed the Public API one-hour sampling limit.
未知项
具体题集与试验数未列于主表。
工具
禁止工具
推理预算
max
框架
未记录
协议
Humanity’s Last Exam; reasoning only, no tools; auto thinking, max effort; 1M total-token cap; no context compaction.
条件
The System Card says some no-tools problems exceed the Public API one-hour sampling limit; retain the reported 49.8% and source evidence with this reproducibility limitation.
直接支持该成绩
Accuracy57.9%原文 57.9% · 单位 %
公布 未确认
HLE 有工具
设置
Humanity’s Last Exam; web search, web fetch, programmatic tool calling and code execution; auto thinking and max effort; 1M total-token cap; no context compaction; Opus 4.6 transcript review/regrade for confirmed answer retrieval.
未知项
具体题集与试验数未列于主表。
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; auto thinking, max effort; 1M total-token cap; no context compaction.
条件
Opus 4.6 transcript review and regrade were used to confirm HLE answer retrieval.
Claude Opus 4.8 · Humanity's Last Exam (2,500-question benchmark) · Main text evidence (ev-op48-hle)
Official source for Humanity's Last Exam · 2,500-question benchmark in Claude Opus 4.8. See “Introducing Claude Opus 4.8” at Humanity's Last Exam 行. Evidence ev-op48-hle.
Claude Opus 4.8 · Humanity's Last Exam (2,500-question benchmark), configuration HLE 无工具, Accuracy 49.8% (exact score publication date unconfirmed). See “Introducing Claude Opus 4.8” at Humanity's Last Exam 行. View score conditions
Claude Opus 4.8 · Humanity's Last Exam (2,500-question benchmark), configuration HLE 有工具, Accuracy 57.9% (exact score publication date unconfirmed). See “Introducing Claude Opus 4.8” at Humanity's Last Exam 行. View score conditions
Unconfirmed · Launch or later disclosure unconfirmed
Collected
Historical basis
No reliable historical version evidence available
Citation text
Claude Opus 4.8 · Humanity's Last Exam (2,500-question benchmark), configuration HLE 无工具, Accuracy 49.8% (exact score publication date unconfirmed); Claude Opus 4.8 · Humanity's Last Exam (2,500-question benchmark), configuration HLE 有工具, Accuracy 57.9% (exact score publication date unconfirmed). Official source: Introducing Claude Opus 4.8 (Main text, 官方发布页;本地保存 HTML/TXT 与主表 PNG:本地留存副本、本地留存副本、本地留存副本;原文发布日期 2026-05-28,当前修订时间未知), Humanity's Last Exam 行, https://www.anthropic.com/news/claude-opus-4-8#opus-48s-capabilities. Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-4-8/ev-op48-hle/?lang=en
Related scores and conditions
Claude Opus 4.8 · Humanity's Last Exam scores and configurations
Metric and score
Configuration and evaluation conditions
Evidence relation
Accuracy49.8%Reported 49.8% · Unit %
Published Unconfirmed
HLE 无工具
Settings
Humanity’s Last Exam; reasoning only, no tools; auto thinking and max effort; 1M total-token cap; no context compaction. Some items exceed the Public API one-hour sampling limit.
Unknowns
具体题集与试验数未列于主表。
Tools
Tools forbidden
Reasoning budget
max
Framework
not recorded
Protocol
Humanity’s Last Exam; reasoning only, no tools; auto thinking, max effort; 1M total-token cap; no context compaction.
Conditions
The System Card says some no-tools problems exceed the Public API one-hour sampling limit; retain the reported 49.8% and source evidence with this reproducibility limitation.
Directly supports this score
Accuracy57.9%Reported 57.9% · Unit %
Published Unconfirmed
HLE 有工具
Settings
Humanity’s Last Exam; web search, web fetch, programmatic tool calling and code execution; auto thinking and max effort; 1M total-token cap; no context compaction; Opus 4.6 transcript review/regrade for confirmed answer retrieval.
Unknowns
具体题集与试验数未列于主表。
Tools
Tools allowed
Reasoning budget
max
Framework
not recorded
Protocol
Humanity’s Last Exam with web search, web fetch, programmatic tool calling and code execution; auto thinking, max effort; 1M total-token cap; no context compaction.
Conditions
Opus 4.6 transcript review and regrade were used to confirm HLE answer retrieval.