OpenAI GPT-5.6 August Update System Card - HealthBench Hard: leaderboard
Table 6 (HealthBench) of OpenAI's GPT-5.6 August Update System Card (Deployment Safety Hub, 2026-08-06): length-adjusted HealthBench Hard score, the headline figure printed before the unadjusted score and mean response length. 0-100, higher is better. Safety evaluations run each model at its lowest reasoning setting. GPT-5.6 Sol/Luna (August 2026) are the checkpoints released that day.
Metric: Length-Adjusted Score (0-100). Source: deploymentsafety.openai.com. Saturation forecast: Around August 2028. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol (August 2026) | 31.4 | |
| 2 | GPT-5.6 Luna (August 2026) | 28.7 | |
| 3 | GPT-5.5 Instant | 22.9 | #127 |
| 4 | GPT-5.3 Instant | 20.2 | #47 |
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-august-update-system-card-healthbench-hard · How It Works · Data refreshed daily, snapshot 2026-11-05.