OpenAI GPT-6 Astra System Card - TroubleshootingBench: 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): identifying and fixing real errors in expert-written lab protocols that rely on tacit knowledge. pass@1, percent, higher is better; the card's High threshold is 36.4%. 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. Saturation forecast: Around December 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 63.46 | #5 |
| 2 | GPT-6.1 Sol | 47.96 | #6 |
| 3 | GPT-6 Sol | 45.3 | #17 |
| 4 | GPT-6 Luna | 38.6 | #62 |
No result here: #3 Claude Opus 5.5, #9 Gemini 4 Argon, #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-6-astra-system-card-troubleshootingbench · How It Works · Data refreshed daily, snapshot 2026-11-07.