OpenAI GPT-5.6 System Card - HealthBench: leaderboard
HealthBench health conversations graded against physician-written rubrics, on the length-adjusted scale the card headlines; OpenAI's own runs as published in the GPT-5.6 system card.
Metric: Length-Adjusted Score (0-100). Source: deploymentsafety.openai.com. Saturation forecast: Around 2028. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 57.7 | #98 |
| 2 | GPT-5.6 Sol | 57 | #19 |
| 3 | GPT-5.6 Terra | 57 | #41 |
| 4 | GPT-5.2 | 56.8 | #110 |
| 5 | GPT-5.5 | 56.5 | #31 |
| 6 | GPT-5.6 Luna | 55.8 | #68 |
| 7 | GPT-5.4 | 54 | #79 |
| 8 | GPT-5.1 | 50.9 | #135 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-5-6-system-card-healthbench · How It Works · Data refreshed daily, snapshot 2026-10-20.