OpenAI GPT-6 Astra System Card - SHP2 Protein Function Prediction: leaderboard
Table 13 of OpenAI's GPT-6 Astra System Card (Deployment Safety Hub, 2026-09-03): models predict held-out SHP2 mutant assay results from structures and partial assay data. Mean R-squared across three assay datasets, higher is better (indicative threshold 0.60). GPT-6 Astra's 0.40 is its production score; a helpful-only variant scored 0.35. GPT-6 Sol's 0.273 comes from Table 34 of the card's section 11 (GPT-6 Sol and GPT-6 Luna, added 2026-09-22).
Metric: Mean R² (three assay datasets). Source: deploymentsafety.openai.com. Source: deploymentsafety.openai.com. Saturation forecast: Around March 2028. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 0.4 | #6 |
| 2 | GPT-6.1 Sol | 0.33 | #7 |
| 3 | GPT-5.6 Sol | 0.3 | #22 |
| 4 | GPT-6 Sol | 0.27 | #19 |
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-shp2-protein-function-prediction · How It Works · Data refreshed daily, snapshot 2026-11-05.