Claude Sonnet 5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations) · 附件证据(ev5-healthbench)

Claude Sonnet 5 的 HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations 官方出处。见《Claude Sonnet 5 System Card》§8.12.1 Figure 8.12.1.A, PDF p.137。证据 ev5-healthbench。

原文与定位

1 HealthBench results HealthBench 32 is an open-source evaluation developed to assess safety, accuracy, and communication across realistic healthcare contexts.
官方材料
Claude Sonnet 5 System Card · PDF 第 137 页
定位
附件 · §8.12.1 Figure 8.12.1.A, PDF p.137
材料版本
PDF with changelog dated 2026-07-10; 146 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 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),披露记录。官方出处 Claude Sonnet 5 System Card(附件,PDF with changelog dated 2026-07-10; 146 pages; collected 2026-11-10)§8.12.1 Figure 8.12.1.A, PDF p.137,https://www.anthropic.com/claude-sonnet-5-system-card#page=137。Benchlog https://benchlog.lekshome.cc/evidence/claude-sonnet-5/ev5-healthbench/

关联成绩与条件

此摘录未关联到已收录的成绩记录。