Virology Benchmark — leaderboard
Metric: Accuracy (%). Source: www.virologytest.ai. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O3 | 43.8 |
| 2 | Gemini 2.5 Pro | 37.6 |
| 3 | O4 Mini | 37 |
| 4 | O1 | 35.4 |
| 5 | Claude 3.7 Sonnet | 30.8 |
| 6 | GPT-4.5 (Preview) | 28.3 |
| 7 | Human Expert | 22.1 |
| 8 | GPT-4o | 18.8 |
Interactive version: theaggregate.ai/benchmark?slug=virology-benchmark · How the rankings work · Data refreshed daily, snapshot 2026-07-22.