OpenAI GPT-6 Astra System Card - Multimodal Troubleshooting Virology: leaderboard
Table 33 (biological capability, High threshold) of OpenAI's GPT-6 Astra System Card, section 11 (GPT-6 Sol and GPT-6 Luna, added 2026-09-22): multiple-choice virology questions on troubleshooting wet-lab protocols, some with images. pass@1, percent, higher is better; the card's High threshold is 31%. GPT-6 Sol and GPT-6 Luna only; the Astra section prints this evaluation as a figure.
Metric: pass@1 (%). Source: deploymentsafety.openai.com. Source: deploymentsafety.openai.com. Source: deploymentsafety.openai.com. Saturation forecast: Around May 2028. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 63.11 | #5 |
| 2 | GPT-6.1 Sol | 55.34 | #9 |
| 3 | GPT-6.1 Terra | 52.54 | #17 |
| 4 | GPT-6 Sol | 50.6 | #22 |
| 5 | GPT-6 Luna | 49.1 | #90 |
No result here: #4 Claude Opus 5.5, #10 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-6-astra-system-card-multimodal-troubleshooting-virology · How It Works · Data refreshed daily, snapshot 2026-11-08.