AA-Omniscience Index - Health: leaderboard
Artificial Analysis's AA-Omniscience Index on the Health questions of its 3,000-question v1.1 factual-recall benchmark: the share of correct answers minus the share of incorrect ones, bounded -100 to 100, so abstaining beats guessing wrong. Higher is better and negative scores are common. Scores are not directly comparable with v1, which had 6,000 questions. Not the accuracy carried by the frozen AA Omniscience domain boards.
Metric: Omniscience Index. Source: artificialanalysis.ai. Saturation forecast: Around 2029. 117 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Carbon (High) | 41.78 | #1 (Gemini 4 Carbon) |
| 2 | Gemini 4 Argon (High) | 34.22 | #9 (Gemini 4 Argon) |
| 3 | GPT-6 Astra (High) | 22.22 | #6 (GPT-6 Astra) |
| 4 | GPT-6 Astra (xHigh) | 20.44 | #6 (GPT-6 Astra) |
| 5 | Muse Wonder Full (Max) | 20.22 | #12 (Muse Wonder Full) |
| 6 | Muse Spark Open (xHigh) | 19.78 | #42 (Muse Spark Open) |
| 7 | GPT-6 Astra (Max) | 19.33 | #6 (GPT-6 Astra) |
| 8 | GPT-6.1 Sol (Max) | 18.67 | #7 (GPT-6.1 Sol) |
| 9 | Grok 4.7 (High) | 18 | #26 (Grok 4.7) |
| 10 | GPT-6.1 Sol (xHigh) | 17.78 | #7 (GPT-6.1 Sol) |
| 11 | Grok 4.7 (xHigh) | 16.89 | #26 (Grok 4.7) |
| 12 | GPT-6 Astra (Low) | 16.44 | #6 (GPT-6 Astra) |
| 13 | GPT-6.1 Sol (High) | 16.44 | #7 (GPT-6.1 Sol) |
| 14 | GPT-6.1 Sol (Low) | 16.22 | #7 (GPT-6.1 Sol) |
| 15 | Kimi K3.1 Pro | 15.33 | #17 |
No result here: #3 Claude Opus 5.5, #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=aa-omniscience-index-health · How It Works · Data refreshed daily, snapshot 2026-11-05.