AA Omniscience - Health — leaderboard
Metric: Accuracy (%). Source: artificialanalysis.ai. 449 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol (High) | 50.7 |
| 2 | GPT-5.6 Sol (Max) | 50.5 |
| 3 | GPT-5.6 Sol (Low) | 50.3 |
| 4 | GPT-5.6 Sol (xHigh) | 49.7 |
| 5 | Grok Build 0.1 | 48.9 |
| 6 | GPT-5.5 (Medium) | 48.8 |
| 7 | GPT-5.5 (xHigh) | 48.7 |
| 8 | GPT-5.6 Sol (Medium) | 48.6 |
| 9 | Grok 4.5 (High) | 48.5 |
| 10 | GPT-5.5 (High) | 47.8 |
| 11 | GPT-5.3 Codex (xHigh) | 46.9 |
| 12 | Gemini 3 Pro (Preview) (High) | 46.8 |
| 13 | GPT-5.5 (Low) | 45.8 |
| 14 | GPT-5.4 (xHigh) | 45.6 |
| 15 | Gemini 3.1 Pro (Preview) | 45.2 |
Interactive version: theaggregate.ai/benchmark?slug=aa-omniscience-health · How the rankings work · Data refreshed daily, snapshot 2026-07-22.