HealthBench Consensus · System-card evaluation; exact dataset version unspecified · 测试定义与成绩

HealthBench Consensus · System-card evaluation; exact dataset version unspecified 收录 7 次模型发布的评测披露或成绩。

测试版本与指标

  • Length-adjusted score (0–100) · score · 越高越好
  • Unadjusted score (0–100) · score · 越高越好
  • Mean response length · characters · 排序方向未确认
  • Score(raw/length-adjusted未注明) · % · 排序方向未确认

各系列最新模型 · 公布成绩

常规展示范围。排名按指标与评测协议分组,已记录的工具、预算及框架分别展示。条件未说明的组保留公布值供查证。

Length-adjusted score (0–100) score

System-card HealthBench table: length-adjusted score (unadjusted score, mean response length in characters).

HealthBench Consensus · System-card evaluation; exact dataset version unspecified · Length-adjusted score (0–100) · System-card HealthBench table: length-adjusted score (unadjusted score, mean response length in characters).
模型与配置成绩(score)记录与证据
GPT-6.1 Terra未注明95.1 score

System-card Table 7: length-adjusted score (unadjusted score, mean response length in characters).

HealthBench Consensus · System-card evaluation; exact dataset version unspecified · Length-adjusted score (0–100) · System-card Table 7: length-adjusted score (unadjusted score, mean response length in characters).
模型与配置成绩(score)记录与证据
GPT-6 Luna未注明95.9 score

Unadjusted score (0–100) score

System-card HealthBench table: length-adjusted score (unadjusted score, mean response length in characters).

HealthBench Consensus · System-card evaluation; exact dataset version unspecified · Unadjusted score (0–100) · System-card HealthBench table: length-adjusted score (unadjusted score, mean response length in characters).
模型与配置成绩(score)记录与证据
GPT-6.1 Terra未注明94.8 score

System-card Table 7: unadjusted score paired with the length-adjusted score.

HealthBench Consensus · System-card evaluation; exact dataset version unspecified · Unadjusted score (0–100) · System-card Table 7: unadjusted score paired with the length-adjusted score.
模型与配置成绩(score)记录与证据
GPT-6 Luna未注明95.6 score

Mean response length characters

System-card HealthBench table: length-adjusted score (unadjusted score, mean response length in characters).

HealthBench Consensus · System-card evaluation; exact dataset version unspecified · Mean response length · System-card HealthBench table: length-adjusted score (unadjusted score, mean response length in characters).
模型与配置成绩(characters)记录与证据
GPT-6.1 Terra未注明1312 characters

System-card Table 7: mean response length paired with adjusted and unadjusted scores.

HealthBench Consensus · System-card evaluation; exact dataset version unspecified · Mean response length · System-card Table 7: mean response length paired with adjusted and unadjusted scores.
模型与配置成绩(characters)记录与证据
GPT-6 Luna未注明1235 characters

历史记录 · 7 次发布

  • GPT-6.1 Terra本次发布有 3 条成绩记录,含 3 条精确值(可含历史记录)
  • GPT-6.1 Sol本次发布有 3 条成绩记录,含 3 条精确值(可含历史记录)
  • GPT-6 Luna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本次发布有 3 条成绩记录,含 3 条精确值(可含历史记录)
  • GPT-5.4本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
  • GPT-5本次发布有 2 条成绩记录,含 2 条精确值(可含历史记录)
  • GPT-5 mini本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)