Home Model series GPT unsuffixed models GPT-5.5 GPT-5.5 · HealthBench Professional · 525 physician-authored conversations · Scores and configurations GPT-5.5 · HealthBench Professional · 525 physician-authored conversations · Scores and configurations GPT-5.5 record for HealthBench Professional · 525 physician-authored conversations. 5 score records for this release, including 5 exact values (may include historical records). Includes 2 source locations.
Scores and evaluation conditions GPT-5.5 · HealthBench Professional scores and configurations Metric and score Configuration and evaluation conditions Sources 长度校正分(0–100) 51.8 score Reported 51.8% · Unit score Published Unconfirmed
GPT-5.5 model-level safety evaluation Settings GPT-5.5 model results for the production release; each benchmark has its stated prompt, task, and safeguard conditions. Unknowns The card does not state one universal system prompt, reasoning effort, or sampling configuration across evaluations. Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol 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。 Conditions Length-adjusted score for HealthBench Professional. 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。 未校正分(0–100) 57.2 score Reported 57.2% · Unit score Published Unconfirmed
GPT-5.5 model-level safety evaluation Settings GPT-5.5 model results for the production release; each benchmark has its stated prompt, task, and safeguard conditions. Unknowns The card does not state one universal system prompt, reasoning effort, or sampling configuration across evaluations. Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol 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。 Conditions Unadjusted score for HealthBench Professional. 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。 Mean response length 3818 characters Reported 3818 · Unit characters Published Unconfirmed
Conflicting results are pending review and are excluded from exact rankings.
GPT-5.5 model-level safety evaluation Settings GPT-5.5 model results for the production release; each benchmark has its stated prompt, task, and safeguard conditions. Unknowns The card does not state one universal system prompt, reasoning effort, or sampling configuration across evaluations. Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol 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。 Conditions Table 7 reports mean response length as 3818; the following prose reports 3893 for GPT-5.5. Both source values are retained. Mean response length 3893 characters Reported 3893 characters · Unit characters Published Unconfirmed
Conflicting results are pending review and are excluded from exact rankings.
GPT-5.5 model-level safety evaluation Settings GPT-5.5 model results for the production release; each benchmark has its stated prompt, task, and safeguard conditions. Unknowns The card does not state one universal system prompt, reasoning effort, or sampling configuration across evaluations. Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol 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。 Conditions Body text reports 3893 characters, conflicting with Table 7's 3818; no correction notice is provided. 相对 GPT-5.4 的长度校正分差 3.7 points Reported +3.7 · Unit points Published Unconfirmed
GPT-5.5 model-level safety evaluation Settings GPT-5.5 model results for the production release; each benchmark has its stated prompt, task, and safeguard conditions. Unknowns The card does not state one universal system prompt, reasoning effort, or sampling configuration across evaluations. Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol 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。 Conditions Change in length-adjusted HealthBench Professional score versus GPT-5.4.
Benchmark versions and metrics Aliases HealthBench Professional
Raw score · % · Higher is better Length-adjusted score · % · Higher is better Score · % · Higher is better Mean response length · characters · Ranking direction unconfirmed 长度校正分(0–100) · score · Higher is better 未校正分(0–100) · score · Higher is better 相对 GPT-5.4 的长度校正分差 · points · Ranking direction unconfirmed Unadjusted score · % · Higher is better