GPT-5.6 Sol on HealthBench Professional
rank 2 of 9 · updated August 16, 2026
GPT-5.6 Sol scores 0.605 on HealthBench Professional, rank 2 of 9 evaluated models. The flagship tier of OpenAI's GPT-5.6 family, aimed at its hardest reasoning and agentic workloads. HealthBench Professional scores models on 525 tasks drawn from real clinician conversations, graded criterion by criterion against physician-written rubrics on a 0 to 1 scale.
Result and API facts
| rank | 2 of 9 |
|---|---|
| score | 0.605 |
| lab | OpenAI |
| context window | 1.1M tokens |
| API price per 1M tokens | $5.00 in / $30.00 out |
| license | proprietary |
| released | 2026-07-09 |
Position in the field
The gap to the leader, Claude Fable 5 at 0.660, is 0.055. Directly below sits Claude Opus 5 at 0.598. Scores on this page come from the same evaluation run, so differences between models are differences on identical tasks, not across configurations.
What does GPT-5.6 Sol score on HealthBench Professional?
GPT-5.6 Sol scores 0.605 on HealthBench Professional, which places it at rank 2 of 9 evaluated models as of August 16, 2026.
How much does GPT-5.6 Sol cost to run?
GPT-5.6 Sol is priced at $5.00 per million input tokens and $30.00 per million output tokens through OpenAI's API.
Head to head
Pairings with a dedicated comparison page are linked; every other difference is in the score-difference matrix.
- 0.605 vs 0.660 · Claude Fable 5 by 0.055
- 0.605 vs 0.598 · GPT-5.6 Sol by 0.007
- GPT-5.6 Sol vs Claude Sonnet 50.605 vs 0.578 · GPT-5.6 Sol by 0.027
- GPT-5.6 Sol vs GPT-5.6 Terra0.605 vs 0.577 · GPT-5.6 Sol by 0.028
- GPT-5.6 Sol vs Claude Opus 4.80.605 vs 0.558 · GPT-5.6 Sol by 0.047
- GPT-5.6 Sol vs GPT-5.6 Luna0.605 vs 0.557 · GPT-5.6 Sol by 0.048
- GPT-5.6 Sol vs GPT-5.5 Instant0.605 vs 0.384 · GPT-5.6 Sol by 0.221
- GPT-5.6 Sol vs MAI-Thinking-10.605 vs 0.350 · GPT-5.6 Sol by 0.255
How tasks are selected and graded is on the methodology page. The full ranking is on the leaderboard.