OpenAI GPT-6 Astra System Card - HealthBench Hard: leaderboard
Table 29 of OpenAI's GPT-6 Astra System Card, section 11 (GPT-6 Sol and GPT-6 Luna, added 2026-09-22): the hard subset of HealthBench, the conversations frontier models still fail, on the length-adjusted scale (0-100), higher is better. GPT-6 Astra, GPT-6 Sol and GPT-6 Luna only; the table's GPT-5.5 and GPT-5.6 columns repeat the GPT-5.6 card. Astra's value is the one the card corrected on 2026-09-22 for a misconfigured earlier run.
Metric: Length-Adjusted Score (0-100). Source: deploymentsafety.openai.com. Source: deploymentsafety.openai.com. Source: deploymentsafety.openai.com. Saturation forecast: Around 2029. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 36.6 | #5 |
| 2 | GPT-6.1 Sol | 36.2 | #9 |
| 3 | GPT-6 Luna | 31.4 | #90 |
| 4 | GPT-6.1 Terra | 31.4 | #17 |
| 5 | GPT-6 Sol | 30.1 | #22 |
No result here: #4 Claude Opus 5.5, #10 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-6-astra-system-card-healthbench-hard · How It Works · Data refreshed daily, snapshot 2026-11-08.