Claude Opus 5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations) · 附件证据(ev-op5-card-healthbench)

Claude Opus 5 的 HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations 官方出处。见《Claude Opus 5 System Card》System Card PDF p.188, §8.15.1 and Figure 8.15.1.A。证据 ev-op5-card-healthbench。

原文与定位

Claude Opus 5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),HealthBench · max配置,Raw score 67.1%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF p.188, §8.15.1 and Figure 8.15.1.A。 查看成绩条件

Claude Opus 5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),HealthBench · max配置,Length-adjusted score 57.8%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF p.188, §8.15.1 and Figure 8.15.1.A。 查看成绩条件

Claude Opus 5: raw score 67.1%; length-adjusted score 57.8%. Max effort, no tools or customized system prompt, Opus 4.8 grader, five-trial average.
官方材料
Claude Opus 5 System Card · PDF 第 188 页
定位
附件 · System Card PDF p.188, §8.15.1 and Figure 8.15.1.A
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 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),HealthBench · max配置,Raw score 67.1%(具体成绩公布时间未确认);Claude Opus 5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),HealthBench · max配置,Length-adjusted score 57.8%(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.188, §8.15.1 and Figure 8.15.1.A,https://www.anthropic.com/claude-opus-5-system-card#page=188。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5/ev-op5-card-healthbench/

关联成绩与条件

Claude Opus 5 · HealthBench 成绩与配置
指标与成绩配置与评测条件证据关系
Raw score67.1%原文 67.1% · 单位 %
公布 未确认
HealthBench · max
设置
Max effort; no tools or customized system prompts; Opus 4.8 grader; five-trial average; length-adjustment method cited from the GPT-5.5 system card.
未知项
未另记
工具
禁止工具
推理预算
max
框架
未记录
协议
HealthBench; raw rubric score.
条件
Max effort; no tools or customized system prompt; Opus 4.8 grader; five-trial average.

直接支持该成绩

在排名中查看此成绩
Length-adjusted score57.8%原文 57.8% · 单位 %
公布 未确认
HealthBench · max
设置
Max effort; no tools or customized system prompts; Opus 4.8 grader; five-trial average; length-adjustment method cited from the GPT-5.5 system card.
未知项
未另记
工具
禁止工具
推理预算
max
框架
未记录
协议
HealthBench; length-adjusted score.
条件
Max effort; no tools or customized system prompt; Opus 4.8 grader; five-trial average.

直接支持该成绩

在排名中查看此成绩