Loading data...
AA Omniscience: leaderboard
AA-Omniscience: factual recall and hallucination rates across 6,000 questions in Law, Health, Business, SWE, Humanities, and Science/Math.
Metric: Score. Source: artificialanalysis.ai. Status: saturation imminent. 514 models tracked.
Top models
| # | Model | Score |
|---|
| 1 | GPT-6 (High) | 43.73 |
| 2 | Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) | 43.45 |
| 3 | GPT-6 (xHigh) | 43.42 |
| 4 | GPT-6 (Max) | 43.4 |
| 5 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | 43.3 |
| 6 | Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) | 42.38 |
| 7 | GPT-6 (Medium) | 42.22 |
| 8 | Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) | 40.8 |
| 9 | GPT-6 (Low) | 40.55 |
| 10 | Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback) | 37.6 |
| 11 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | 37.07 |
| 12 | Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) | 35.38 |
| 13 | Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback) | 34.13 |
| 14 | Claude Opus 5 (Adaptive Reasoning, High Effort) | 33.72 |
| 15 | Gemini 3.1 Pro (Preview) | 31.88 |
Interactive version: theaggregate.ai/benchmark?slug=aa-omniscience · How It Works · Data refreshed daily, snapshot 2026-09-05.