GPT Sol · HealthBench Professional · 525 physician-authored conversations · 历代记录

按发布时间查看 GPT Sol 的 4 次发布在 HealthBench Professional · 525 physician-authored conversations 的成绩、配置与披露。

仅为直接前代间的唯一、有效精确值计算差值,要求单位、指标与明确记录的配置和条件一致。

GPT-5.6 Sol

· 本次发布有 4 条成绩记录,含 4 条精确值(可含历史记录)

GPT-5.6 Sol · HealthBench Professional 成绩与配置
指标与成绩配置与评测条件出处
Score60.5%原文 60.5% · 单位 %
公布 未确认
GPT-5.6 Sol table result
设置
GPT-5.6 Sol; article table does not print the effort label for this row.
未知项
Effort may be identified by a matching loaded chart; otherwise it remains unknown.
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
未说明
条件
GPT-5.6 Sol; effort is not printed in the table. Official scoring approach; source warns results are not comparable with Anthropic system-card scores.
在排名中查看此成绩
长度校正分(0–100)60.5 score原文 60.5 · 单位 score
公布 未确认
GPT-5.6 Sol HealthBench evaluations
设置
HealthBench and HealthBench Professional-family evaluations; table reports length-adjusted scores.
未知项
Reasoning effort、Grader version for each GPT-5.6 score、System-level safeguards、Exact benchmark data snapshot
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 penalty is 1.47 points per 500 characters beyond 2,000; response length 3,228 characters. 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。
在排名中查看此成绩
未校正分(0–100)64.1 score原文 64.1 · 单位 score
公布 未确认
GPT-5.6 Sol HealthBench evaluations
设置
HealthBench and HealthBench Professional-family evaluations; table reports length-adjusted scores.
未知项
Reasoning effort、Grader version for each GPT-5.6 score、System-level safeguards、Exact benchmark data snapshot
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 reports the tuple as length-adjusted score (unadjusted score, mean response length in characters). 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。
在排名中查看此成绩
Mean response length3228 characters原文 3228 · 单位 characters
公布 未确认
GPT-5.6 Sol HealthBench evaluations
设置
HealthBench and HealthBench Professional-family evaluations; table reports length-adjusted scores.
未知项
Reasoning effort、Grader version for each GPT-5.6 score、System-level safeguards、Exact benchmark data snapshot
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 reports the tuple as length-adjusted score (unadjusted score, mean response length in characters).
在排名中查看此成绩

GPT-6 Sol

· 本次发布有 3 条成绩记录,含 3 条精确值(可含历史记录)

GPT-6 Sol · HealthBench Professional 成绩与配置
指标与成绩配置与评测条件出处
长度校正分(0–100)60.8 score原文 60.8 · 单位 score
公布 未确认
GPT-6 Sol, system-card comparison configuration unspecified
设置
GPT-6 Sol; system-card comparison table does not identify reasoning effort or serving configuration.
未知项
Reasoning effort not stated、Sampling and tool settings not stated
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
System-card Table 7: length-adjusted score (unadjusted score, mean response length in characters).
条件
GPT-6 Sol; effort unspecified. The card warns comparison values for previously launched models may reflect later versions and differ from launch.
在排名中查看此成绩
未校正分(0–100)59.5 score原文 59.5 · 单位 score
公布 未确认
GPT-6 Sol, system-card comparison configuration unspecified
设置
GPT-6 Sol; system-card comparison table does not identify reasoning effort or serving configuration.
未知项
Reasoning effort not stated、Sampling and tool settings not stated
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
System-card Table 7: unadjusted score paired with the length-adjusted score.
条件
GPT-6 Sol; effort unspecified. The card warns comparison values for previously launched models may reflect later versions and differ from launch.
在排名中查看此成绩
Mean response length1573 characters原文 1573 · 单位 characters
公布 未确认
GPT-6 Sol, system-card comparison configuration unspecified
设置
GPT-6 Sol; system-card comparison table does not identify reasoning effort or serving configuration.
未知项
Reasoning effort not stated、Sampling and tool settings not stated
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
System-card Table 7: mean response length paired with adjusted and unadjusted scores.
条件
GPT-6 Sol; effort unspecified. The card warns comparison values for previously launched models may reflect later versions and differ from launch.
在排名中查看此成绩

GPT-6.1 Sol

· 本次发布有 3 条成绩记录,含 3 条精确值(可含历史记录)

与直接前代的记录缺少满足差值计算的同条件依据。

GPT-6.1 Sol · HealthBench Professional 成绩与配置
指标与成绩配置与评测条件出处
长度校正分(0–100)64.2 score原文 64.2 · 单位 score
公布 未确认
GPT-6.1 Sol, system-card configuration unspecified
设置
GPT-6.1 Sol; system-card comparison table does not identify reasoning effort or serving configuration.
未知项
Reasoning effort not stated、Sampling and tool settings not stated
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
System-card Table 7: length-adjusted score (unadjusted score, mean response length in characters).
条件
GPT-6.1 Sol; reasoning effort unspecified. The card notes comparison scores for previously launched models may reflect later model versions and differ from their launch values.
在排名中查看此成绩
未校正分(0–100)67.2 score原文 67.2 · 单位 score
公布 未确认
GPT-6.1 Sol, system-card configuration unspecified
设置
GPT-6.1 Sol; system-card comparison table does not identify reasoning effort or serving configuration.
未知项
Reasoning effort not stated、Sampling and tool settings not stated
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
System-card Table 7: length-adjusted score (unadjusted score, mean response length in characters).
条件
GPT-6.1 Sol; reasoning effort unspecified. The card notes comparison scores for previously launched models may reflect later model versions and differ from their launch values.
在排名中查看此成绩
Mean response length3038 characters原文 3038 · 单位 characters
公布 未确认
GPT-6.1 Sol, system-card configuration unspecified
设置
GPT-6.1 Sol; system-card comparison table does not identify reasoning effort or serving configuration.
未知项
Reasoning effort not stated、Sampling and tool settings not stated
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
System-card Table 7: length-adjusted score (unadjusted score, mean response length in characters).
条件
GPT-6.1 Sol; reasoning effort unspecified. The card notes comparison scores for previously launched models may reflect later model versions and differ from their launch values.
在排名中查看此成绩

GPT-6.2 Sol

· 本次发布有 3 条成绩记录,含 3 条精确值(可含历史记录)

GPT-6.2 Sol · HealthBench Professional 成绩与配置
指标与成绩配置与评测条件出处
长度校正分(0–100)65.9 score原文 65.9 · 单位 score
公布 未确认
GPT-6.2 Sol, HealthBench Professional configuration unspecified
设置
GPT-6.2 Sol; Table 17 does not state reasoning effort. Length adjustment: 1.47 points per 500 characters above/below 2,000; models are not told the adjustment.
未知项
HealthBench Professional 推理档位未注明、采样、完整 harness 和工具配置未注明
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
Table 17: length-adjusted score (unadjusted score, mean visible response length in characters).
条件
分数为0–100尺度,不是百分比。长度校正以2000字符为基准,每500字符对应1.47分的惩罚或奖励;评测时不向模型告知该校正规则。推理档位及逐项采样设置未注明。
在排名中查看此成绩
未校正分(0–100)65.5 score原文 65.5 · 单位 score
公布 未确认
GPT-6.2 Sol, HealthBench Professional configuration unspecified
设置
GPT-6.2 Sol; Table 17 does not state reasoning effort. Length adjustment: 1.47 points per 500 characters above/below 2,000; models are not told the adjustment.
未知项
HealthBench Professional 推理档位未注明、采样、完整 harness 和工具配置未注明
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
Table 17: length-adjusted score (unadjusted score, mean visible response length in characters).
条件
分数为0–100尺度,不是百分比。长度校正以2000字符为基准,每500字符对应1.47分的惩罚或奖励;评测时不向模型告知该校正规则。推理档位及逐项采样设置未注明。
在排名中查看此成绩
Mean response length1869 characters原文 1,869 · 单位 characters
公布 未确认
GPT-6.2 Sol, HealthBench Professional configuration unspecified
设置
GPT-6.2 Sol; Table 17 does not state reasoning effort. Length adjustment: 1.47 points per 500 characters above/below 2,000; models are not told the adjustment.
未知项
HealthBench Professional 推理档位未注明、采样、完整 harness 和工具配置未注明
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
Table 17: length-adjusted score (unadjusted score, mean visible response length in characters).
条件
分数为0–100尺度,不是百分比。长度校正以2000字符为基准,每500字符对应1.47分的惩罚或奖励;评测时不向模型告知该校正规则。推理档位及逐项采样设置未注明。
在排名中查看此成绩