OpenAI GPT-5.5 System Card - Biochemistry Knowledge Improvement: leaderboard
Biosecurity capability slice from OpenAI's GPT-5.5 system card — biochemistry knowledge uplift evaluation; OpenAI-run frontier comparison.
Metric: reward@4 (%). Source: deploymentsafety.openai.com. Saturation forecast: Around June 2028. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 Pro | 39.26 | #17 |
| 2 | GPT-5.5 | 32.32 | #31 |
| 3 | GPT-5.4 (Thinking) | 30.97 | #79 (GPT-5.4) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-5-5-system-card-biochemistry-knowledge-improvement · How It Works · Data refreshed daily, snapshot 2026-10-20.