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. Saturation forecast: Around October 2027. 580 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra (High) | 43.73 | #6 (GPT-6 Astra) |
| 2 | GPT-6 Astra (xHigh) | 43.42 | #6 (GPT-6 Astra) |
| 3 | GPT-6 Astra (Max) | 43.4 | #6 (GPT-6 Astra) |
| 4 | Gemini 4 Argon (High) | 42.35 | #8 (Gemini 4 Argon) |
| 5 | GPT-6 Astra (Medium) | 42.22 | #6 (GPT-6 Astra) |
| 6 | GPT-6.1 Sol (Max) | 41.53 | #7 (GPT-6.1 Sol) |
| 7 | GPT-6.1 Sol (High) | 41.45 | #7 (GPT-6.1 Sol) |
| 8 | GPT-6.1 Sol (xHigh) | 40.87 | #7 (GPT-6.1 Sol) |
| 9 | GPT-6 Astra (Low) | 40.55 | #6 (GPT-6 Astra) |
| 10 | GPT-6.1 Sol (Medium) | 39.95 | #7 (GPT-6.1 Sol) |
| 11 | GPT-6.1 Sol (Low) | 37.63 | #7 (GPT-6.1 Sol) |
| 12 | Claude Opus 5 (Max) | 37.07 | #12 (Claude Opus 5) |
| 13 | Claude Opus 5 (xHigh) | 35.38 | #12 (Claude Opus 5) |
| 14 | Claude Opus 5 (High) | 33.72 | #12 (Claude Opus 5) |
| 15 | Grok 4.7 (xHigh) | 32.03 | #25 (Grok 4.7) |
No result here: #3 Claude Opus 5.5, #9 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=aa-omniscience · How It Works · Data refreshed daily, snapshot 2026-10-20.