Home Model series GPT Luna GPT-6 Luna GPT-6 Luna · HealthBench Hard · System-card evaluation; exact dataset version unspecified · Scores and configurations GPT-6 Luna · HealthBench Hard · System-card evaluation; exact dataset version unspecified · Scores and configurations GPT-6 Luna record for HealthBench Hard · System-card evaluation; exact dataset version unspecified. 3 score records for this release, including 3 exact values (may include historical records). Includes 1 source location.
Scores and evaluation conditions GPT-6 Luna · HealthBench Hard scores and configurations Metric and score Configuration and evaluation conditions Sources Length-adjusted score (0–100) 31.4 score Reported 31.4 · Unit score Published Unconfirmed
GPT-6 Luna, system-card comparison configuration unspecified Settings GPT-6 Luna; system-card comparison table does not identify reasoning effort or serving configuration. Unknowns Reasoning effort not stated、Sampling and tool settings not stated Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol System-card Table 7: length-adjusted score (unadjusted score, mean response length in characters). Conditions GPT-6 Luna; effort unspecified. The card warns comparison values for previously launched models may reflect later versions and differ from launch. View this score in rankings Unadjusted score (0–100) 25.4 score Reported 25.4 · Unit score Published Unconfirmed
GPT-6 Luna, system-card comparison configuration unspecified Settings GPT-6 Luna; system-card comparison table does not identify reasoning effort or serving configuration. Unknowns Reasoning effort not stated、Sampling and tool settings not stated Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol System-card Table 7: unadjusted score paired with the length-adjusted score. Conditions GPT-6 Luna; effort unspecified. The card warns comparison values for previously launched models may reflect later versions and differ from launch. View this score in rankings Mean response length 1241 characters Reported 1241 · Unit characters Published Unconfirmed
GPT-6 Luna, system-card comparison configuration unspecified Settings GPT-6 Luna; system-card comparison table does not identify reasoning effort or serving configuration. Unknowns Reasoning effort not stated、Sampling and tool settings not stated Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol System-card Table 7: mean response length paired with adjusted and unadjusted scores. Conditions GPT-6 Luna; effort unspecified. The card warns comparison values for previously launched models may reflect later versions and differ from launch. View this score in rankings
Benchmark versions and metrics Length-adjusted score (0–100) · score · Higher is better Unadjusted score (0–100) · score · Higher is better Mean response length · characters · Ranking direction unconfirmed Score(raw/length-adjusted未注明) · % · Ranking direction unconfirmed