OpenAI GPT-6 Astra System Card - HealthBench Hard: leaderboard
Metric: Length-Adjusted Score (0-100). Source: deploymentsafety.openai.com. Saturation forecast: Around 2029. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-6 | 36.6 |
| 2 | GPT-6 Luna | 31.4 |
| 3 | GPT-6 Sol | 30.1 |
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-6-astra-system-card-healthbench-hard · How It Works · Data refreshed daily, snapshot 2026-09-24.