GPT-5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations) 67.2% · 附件证据(ev-gpt5-healthbench-score-thinking)

GPT-5 的 HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations 官方出处。GPT-5 thinking (system card) · 67.2%。见《GPT-5 System Card | OpenAI》PDF p. 17, Figure 6 / Realistic health conversations / HealthBench。证据 ev-gpt5-healthbench-score-thinking。

原文与定位

GPT-5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),GPT-5 thinking (system card)配置,Length-adjusted score 67.2%(成绩公布 2025-08-07)。见《GPT-5 System Card | OpenAI》PDF p. 17, Figure 6 / Realistic health conversations / HealthBench。 查看成绩条件

Figure 6, HealthBench (realistic health conversations): gpt-5-thinking 67.2%.
官方材料
GPT-5 System Card | OpenAI · PDF 第 17 页
定位
附件 · PDF p. 17, Figure 6 / Realistic health conversations / HealthBench
材料版本
Actual archived August 7, 2025 launch PDF, 59 pages; text pp.1-59 and all figure/table pages fully reviewed; independent of current 60-page revision. Existing evidence IDs and launch locators retained.
版本公布
披露时间
· 已有首发依据
采集时间
历史依据
Actual launch PDF replay 20250807170752, HTTP 200 application/pdf, digest ORQL27FZQUBZIEDWSFAKB7HOHFDHRPMS; saved 4,842,287-byte 59-page PDF at 2026-11-16-review-gpt-early/本地留存副本; text pp.1-59 and all figure/table pages read. This is not the unrelated one-page placeholder.
引用文本

GPT-5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),GPT-5 thinking (system card)配置,Length-adjusted score 67.2%(成绩公布 2025-08-07)。官方出处 GPT-5 System Card | OpenAI(附件,Actual archived August 7, 2025 launch PDF, 59 pages; text pp.1-59 and all figure/table pages fully reviewed; independent of current 60-page revision. Existing evidence IDs and launch locators retained.)PDF p. 17, Figure 6 / Realistic health conversations / HealthBench,https://web.archive.org/web/20250807170752id_/https://cdn.openai.com/pdf/8124a3ce-ab78-4f06-96eb-49ea29ffb52f/gpt5-system-card-aug7.pdf#page=17。Benchlog https://benchlog.lekshome.cc/evidence/gpt-5/ev-gpt5-healthbench-score-thinking/

关联成绩与条件

GPT-5 · HealthBench 成绩与配置
指标与成绩配置与评测条件证据关系
Length-adjusted score67.2%原文 67.2% · 单位 %
公布
GPT-5 thinking (system card)
设置
System-card reasoning model; effort is not stated for the cited evaluation.
未知项
Exact reasoning effort is not reported for this system-card evaluation.
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
HealthBench, realistic health conversations; score as labeled in Figure 6.
条件
System card target column: gpt-5-thinking (reasoning model; exact reasoning effort is not reported). HealthBench realistic health conversations; Figure 6.

直接支持该成绩

在排名中查看此成绩