GPT-5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations) 54.3% · 附件证据(ev-gpt5-healthbench-score-main-current60)
GPT-5 的 HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations 官方出处。GPT-5 main · 54.3%。见《GPT-5 System Card (current 60-page revision)》Current 60-page PDF p.18, Figure 6, HealthBench; compare archived 59-page p.17.。证据 ev-gpt5-healthbench-score-main-current60。
原文与定位
GPT-5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),GPT-5 main配置,Length-adjusted score 54.3%(成绩公布 2025-08-07)。见《GPT-5 System Card (current 60-page revision)》Current 60-page PDF p.18, Figure 6, HealthBench; compare archived 59-page p.17.。 查看成绩条件
Figure 6, HealthBench (realistic health conversations): gpt-5-main 54.3%.
- 官方材料
- GPT-5 System Card (current 60-page revision) · PDF 第 18 页
- 定位
- 附件 · Current 60-page PDF p.18, Figure 6, HealthBench; compare archived 59-page p.17.
- 材料版本
- Current canonical PDF dated August 13, 2025; text pp.1-60 fully read; all 45 table/figure pages visually inspected, plus p.31; detailed scope in 2026-11-16-review-gpt-early/PROGRESS.md. Exact current revision date 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
GPT-5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),GPT-5 main配置,Length-adjusted score 54.3%(成绩公布 2025-08-07)。官方出处 GPT-5 System Card (current 60-page revision)(附件,Current canonical PDF dated August 13, 2025; text pp.1-60 fully read; all 45 table/figure pages visually inspected, plus p.31; detailed scope in 2026-11-16-review-gpt-early/PROGRESS.md. Exact current revision date unknown.)Current 60-page PDF p.18, Figure 6, HealthBench; compare archived 59-page p.17.,https://cdn.openai.com/gpt-5-system-card.pdf#page=18。Benchlog https://benchlog.lekshome.cc/evidence/gpt-5/ev-gpt5-healthbench-score-main-current60/
关联成绩与条件
| 指标与成绩 | 配置与评测条件 | 证据关系 |
|---|---|---|
| Length-adjusted score54.3%原文 54.3% · 单位 % 公布 | GPT-5 main
| 直接支持该成绩 在排名中查看此成绩 |