OpenAI GPT-5 System Card - Human Pathogen Capabilities Test: leaderboard
The "Human Pathogen Capabilities Test" subtask of OpenAI GPT-5 System Card. A benchmark result reported in the OpenAI GPT-5 system card, as self-reported by the model developer.
Metric: Mean Accuracy (%). Source: cdn.openai.com. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O3 (High) | 58.3 | #124 (O3) |
| 2 | GPT-5 (Thinking) | 53.7 | #98 (GPT-5) |
| 3 | Grok 4 | 51.4 | #181 |
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-5-system-card-human-pathogen-capabilities-test · How It Works · Data refreshed daily, snapshot 2026-10-20.