Claude Sonnet 5.5 · PhysicianBench(100 physician tasks in an electronic health record; pass rate across attempts) · 附件证据(ev55-physicianbench)

Claude Sonnet 5.5 的 PhysicianBench · 100 physician tasks in an electronic health record; pass rate across attempts 官方出处。见《Claude Sonnet 5.5 System Card》§8.15.3-8.15.4, PDF pp.138-139。证据 ev55-physicianbench。

原文与定位

Claude Sonnet 5.5 · PhysicianBench(100 physician tasks in an electronic health record; pass rate across attempts),Max effort配置,Pass rate 63.2%(具体成绩公布时间未确认)。见《Claude Sonnet 5.5 System Card》§8.15.3-8.15.4, PDF pp.138-139。 查看成绩条件

Claude Sonnet 5.5 · PhysicianBench(100 physician tasks in an electronic health record; pass rate across attempts),Low effort配置,Pass rate 27.2%(具体成绩公布时间未确认)。见《Claude Sonnet 5.5 System Card》§8.15.3-8.15.4, PDF pp.138-139。 查看成绩条件

Claude Sonnet 5.5 · PhysicianBench(100 physician tasks in an electronic health record; pass rate across attempts),Medium effort配置,Pass rate 30%(具体成绩公布时间未确认)。见《Claude Sonnet 5.5 System Card》§8.15.3-8.15.4, PDF pp.138-139。 查看成绩条件

At max effort, Claude Sonnet 5.5 passes 63.2% of attempts, well above Claude Sonnet 5 (37.4%), level with Claude Fable 5.1 (61.0%), about 6 points above Claude Opus 5 (57.6%) and about 5 points below Claude Opus 5.5 (68.4%). With 100 tasks, differences of 5 to 6 points are at the edge of what the benchmark can resolve. low and medium effort are not distinguishable (27.2% and 30.0%).
官方材料
Claude Sonnet 5.5 System Card · PDF 第 138 页
定位
附件 · §8.15.3-8.15.4, PDF pp.138-139
材料版本
PDF cover dated 2026-09-28; 148 pages; collected 2026-11-10
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 Sonnet 5.5 · PhysicianBench(100 physician tasks in an electronic health record; pass rate across attempts),Max effort配置,Pass rate 63.2%(具体成绩公布时间未确认);Claude Sonnet 5.5 · PhysicianBench(100 physician tasks in an electronic health record; pass rate across attempts),Low effort配置,Pass rate 27.2%(具体成绩公布时间未确认);Claude Sonnet 5.5 · PhysicianBench(100 physician tasks in an electronic health record; pass rate across attempts),Medium effort配置,Pass rate 30%(具体成绩公布时间未确认)。官方出处 Claude Sonnet 5.5 System Card(附件,PDF cover dated 2026-09-28; 148 pages; collected 2026-11-10)§8.15.3-8.15.4, PDF pp.138-139,https://www.anthropic.com/claude-sonnet-5-5-system-card#page=138。Benchlog https://benchlog.lekshome.cc/evidence/claude-sonnet-5-5/ev55-physicianbench/

关联成绩与条件

Claude Sonnet 5.5 · PhysicianBench 成绩与配置
指标与成绩配置与评测条件证据关系
Pass rate63.2%原文 63.2% · 单位 %
公布 未确认
Max effort
设置
Max reasoning effort.
未知项
Adaptive thinking status is benchmark-specific.
工具
工具条件未记录
推理预算
max
框架
未记录
协议
PhysicianBench, 100 physician EHR tasks.
条件
Max effort; same harness across models; Opus 5 grader.

直接支持该成绩

在排名中查看此成绩
Pass rate27.2%原文 27.2% at Low · 单位 %
公布 未确认
Low effort
设置
Low reasoning effort.
未知项
Sampling settings not stated unless recorded per result.
工具
工具条件未记录
推理预算
low
框架
未记录
协议
PhysicianBench, 100 physician EHR tasks.
条件
Low effort.

直接支持该成绩

在排名中查看此成绩
Pass rate30%原文 30.0% at Medium · 单位 %
公布 未确认
Medium effort
设置
Medium reasoning effort.
未知项
Sampling settings not stated unless recorded per result.
工具
工具条件未记录
推理预算
medium
框架
未记录
协议
PhysicianBench, 100 physician EHR tasks.
条件
Medium effort.

直接支持该成绩

在排名中查看此成绩