GPT-6 Astra · HealthBench Professional(525 physician-authored conversations) · 主文证据(ev-table-6-healthbench-professional)

GPT-6 Astra 的 HealthBench Professional · 525 physician-authored conversations 官方出处。见《GPT-6 Astra System Card》HTML system card Table 6 (#tbl-6); row for HealthBench Professional, gpt-6 Astra column; values transcribed without adding percent signs。证据 ev-table-6-healthbench-professional。

原文与定位

GPT-6 Astra · HealthBench Professional(525 physician-authored conversations),GPT-6 Astra HealthBench corrected system-card values配置,长度校正分(0–100) 64.7 score(成绩公布 2026-09-22)。见《GPT-6 Astra System Card》HTML system card Table 6 (#tbl-6); row for HealthBench Professional, gpt-6 Astra column; values transcribed without adding percent signs。 查看成绩条件

GPT-6 Astra · HealthBench Professional(525 physician-authored conversations),GPT-6 Astra HealthBench corrected system-card values配置,未校正分(0–100) 68.2 score(成绩公布 2026-09-22)。见《GPT-6 Astra System Card》HTML system card Table 6 (#tbl-6); row for HealthBench Professional, gpt-6 Astra column; values transcribed without adding percent signs。 查看成绩条件

GPT-6 Astra · HealthBench Professional(525 physician-authored conversations),GPT-6 Astra HealthBench corrected system-card values配置,Mean response length 3185 characters(成绩公布 2026-09-22)。见《GPT-6 Astra System Card》HTML system card Table 6 (#tbl-6); row for HealthBench Professional, gpt-6 Astra column; values transcribed without adding percent signs。 查看成绩条件

Table 6 caption: length-adjusted score (unadjusted, mean response length in characters); Higher is better. GPT-6 Astra row for HealthBench Professional: 64.7 (68.2, 3185).
官方材料
GPT-6 Astra System Card
定位
主文 · HTML system card Table 6 (#tbl-6); row for HealthBench Professional, gpt-6 Astra column; values transcribed without adding percent signs
材料版本
当前可见 HTML 版本;含 9/22 HealthBench 与 alignment 更新、9/29 dots 附录、10/30 WCB 更正
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-6 Astra · HealthBench Professional(525 physician-authored conversations),GPT-6 Astra HealthBench corrected system-card values配置,长度校正分(0–100) 64.7 score(成绩公布 2026-09-22);GPT-6 Astra · HealthBench Professional(525 physician-authored conversations),GPT-6 Astra HealthBench corrected system-card values配置,未校正分(0–100) 68.2 score(成绩公布 2026-09-22);GPT-6 Astra · HealthBench Professional(525 physician-authored conversations),GPT-6 Astra HealthBench corrected system-card values配置,Mean response length 3185 characters(成绩公布 2026-09-22)。官方出处 GPT-6 Astra System Card(主文,当前可见 HTML 版本;含 9/22 HealthBench 与 alignment 更新、9/29 dots 附录、10/30 WCB 更正)HTML system card Table 6 (#tbl-6); row for HealthBench Professional, gpt-6 Astra column; values transcribed without adding percent signs,https://deploymentsafety.openai.com/gpt-6-astra。Benchlog https://benchlog.lekshome.cc/evidence/gpt-6-astra/ev-table-6-healthbench-professional/

关联成绩与条件

GPT-6 Astra · HealthBench Professional 成绩与配置
指标与成绩配置与评测条件证据关系
长度校正分(0–100)64.7 score原文 64.7 · 单位 score
公布

System Card changelog dated 2026-09-22: HealthBench values for GPT-6 Astra were revised to correct a misconfiguration in previous evaluations.

GPT-6 Astra HealthBench corrected system-card values
设置
System-card values revised on 2026-09-22 to correct misconfiguration in previous evaluations.
未知项
Previous exact value mapping not disclosed in the changelog
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
OpenAI 系统卡 HealthBench 计分;2,000 字符不调整,每多 500 字符减 1.47 分,较短回复对应加分;grader 未说明。
条件
Table 6 current reported row; exact reasoning effort and sampling are not stated. The card changelog identifies HealthBench values as revised for a prior misconfiguration; no unique prior-value mapping is given. 系统卡明确采用 0–100 量表;保留原始分数字符串,不乘除数值。

直接支持该成绩

在排名中查看此成绩
未校正分(0–100)68.2 score原文 68.2 · 单位 score
公布

System Card changelog dated 2026-09-22: HealthBench values for GPT-6 Astra were revised to correct a misconfiguration in previous evaluations.

GPT-6 Astra HealthBench corrected system-card values
设置
System-card values revised on 2026-09-22 to correct misconfiguration in previous evaluations.
未知项
Previous exact value mapping not disclosed in the changelog
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
OpenAI 系统卡 HealthBench 计分;2,000 字符不调整,每多 500 字符减 1.47 分,较短回复对应加分;grader 未说明。
条件
Exact reasoning effort and sampling are not stated. This is the unadjusted score paired with the length-adjusted value in Table 6. 系统卡明确采用 0–100 量表;保留原始分数字符串,不乘除数值。

直接支持该成绩

在排名中查看此成绩
Mean response length3185 characters原文 3185 · 单位 characters
公布

System Card changelog dated 2026-09-22: HealthBench values for GPT-6 Astra were revised to correct a misconfiguration in previous evaluations.

GPT-6 Astra HealthBench corrected system-card values
设置
System-card values revised on 2026-09-22 to correct misconfiguration in previous evaluations.
未知项
Previous exact value mapping not disclosed in the changelog
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
OpenAI 系统卡 HealthBench 计分;2,000 字符不调整,每多 500 字符减 1.47 分,较短回复对应加分;grader 未说明。
条件
Length statistic paired with the length-adjusted and unadjusted scores; exact reasoning effort and sampling are not stated.

直接支持该成绩

在排名中查看此成绩