HealthBench Consensus
Open-ended health conversations graded against physician-written rubrics.
- ModelScoreYour cost / mo
- 1GPT-5.4 · OpenAIbest value96.6 score
- 2GPT-6 Sol · OpenAIbest value96.2 score
- 3GPT-5.5 · OpenAI95.6 score
- 4GPT-5.6 Sol · OpenAI95.5 score
- 5GPT-5.6 Luna · OpenAIbest value95.1 score
- 6GPT-5.6 Terra · OpenAI95.1 score
“Best value”: no other model here reports a higher score at a lower cost for your workload. Scores are self-reported by each maker with different settings, so treat close calls as ties.
How each maker reported it
- GPT-5.4 §3.6, §5.1, §6.3, p.10, p.18–28, p.36
The card reports safety and Preparedness evaluations, not general capability benchmarks. Most values are read from the card's labelled charts; GPT-5.4 mini values come from the card's appendix tables. GPT-5.2 Thinking's Cyber Range rate is a lower bound. The health comparison columns are labelled "GPT-5.4" and "GPT-5.2". CTF is pass@12, Tacit Knowledge cons@32.
- GPT-6 Sol Appendix A, p.120–154
The card reports safety and Preparedness evaluations, not general capability benchmarks. Cyber scores are at maximum reasoning effort; GPT-5.6 Sol cyber values are its maximum scores using more tokens. HealthBench scores are length-adjusted. SandboxBench is targets solved out of 22. Astra values only where the appendix states them.
- GPT-5.5 §5, §9.1, p.12, p.24–39
The card reports safety and Preparedness evaluations, not general capability benchmarks. Several values are read from the card's labelled charts. HealthBench scores are length-adjusted; the card's health comparison column is labelled "GPT-5.4". Biochemistry is reward@4, protein binding pass@4, DNA design pass@1, CTF pass@12, Tacit Knowledge cons@32; Internal Research Debugging is a median score.
- GPT-5.6 Sol p.11–15, p.38–55
The card reports safety and Preparedness evaluations, not general capability benchmarks. HealthBench scores are length-adjusted. Most biology and cyber results are shown only as figures; values appear here only where the text or a table states them, and several (virology, ProtocolQA, TroubleshootingBench, CTF) are given only for the top-scoring GPT-5.6 model. UK AISI and Irregular rows are external evaluations of Sol. GPT-5.5 is the 'gpt-5.5-thinking'/'gpt-5.5' column of the card; its hard-negative score is the corrected 19 Aug 2026 value. Agentic-safety rows are 0–1 scores, higher is better.
- GPT-5.6 Luna p.11–15, p.38–55
The card reports safety and Preparedness evaluations, not general capability benchmarks. HealthBench scores are length-adjusted. Most biology and cyber results are shown only as figures; values appear here only where the text or a table states them, and several (virology, ProtocolQA, TroubleshootingBench, CTF) are given only for the top-scoring GPT-5.6 model. UK AISI and Irregular rows are external evaluations of Sol. GPT-5.5 is the 'gpt-5.5-thinking'/'gpt-5.5' column of the card; its hard-negative score is the corrected 19 Aug 2026 value. Agentic-safety rows are 0–1 scores, higher is better.
- GPT-5.6 Terra p.11–15, p.38–55
The card reports safety and Preparedness evaluations, not general capability benchmarks. HealthBench scores are length-adjusted. Most biology and cyber results are shown only as figures; values appear here only where the text or a table states them, and several (virology, ProtocolQA, TroubleshootingBench, CTF) are given only for the top-scoring GPT-5.6 model. UK AISI and Irregular rows are external evaluations of Sol. GPT-5.5 is the 'gpt-5.5-thinking'/'gpt-5.5' column of the card; its hard-negative score is the corrected 19 Aug 2026 value. Agentic-safety rows are 0–1 scores, higher is better.
Only each model's own maker's number is shown; scores a maker reports for rival models are left out.