OpenAI GPT-5.6 System Card - HealthBench Hard: leaderboard
Metric: Length-Adjusted Score (0-100). Source: deploymentsafety.openai.com. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 34.7 |
| 2 | GPT-5.2 | 34.3 |
| 3 | GPT-5.6 Sol | 33.1 |
| 4 | GPT-5.6 Terra | 32.7 |
| 5 | GPT-5.6 Luna | 32 |
| 6 | GPT-5.5 | 31.5 |
| 7 | GPT-5.4 | 29.1 |
| 8 | GPT-5.1 | 25.4 |
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-5-6-system-card-healthbench-hard · How It Works · Data refreshed daily, snapshot 2026-09-05.