AA-Omniscience v1.1: leaderboard
Artificial Analysis's AA-Omniscience v1.1 knowledge and hallucination benchmark: 3,000 factual-recall questions (300 of them public) across Business, Health, Humanities & Social Sciences, Law, Software Engineering, and Science, Engineering & Mathematics, graded by GPT-5.6 Luna (medium). Net score: the share of correct answers minus the share of incorrect ones, -100 to 100, so abstaining beats guessing wrong; higher is better. v1.1 replaced v1's 6,000 questions by dropping saturated ones and v1's 600 public ones, adding new questions and fixing ambiguous or wrong ones, so scores are not directly comparable with the v1 AA Omniscience board.
Metric: Net Score. Source: artificialanalysis.ai. Saturation forecast: Around April 2028. 134 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Carbon (High) | 53.5 | #2 (Gemini 4 Carbon) |
| 2 | Gemini 4 Carbon (Medium) | 46.77 | #2 (Gemini 4 Carbon) |
| 3 | Gemini 4 Argon (High) | 46.1 | #11 (Gemini 4 Argon) |
| 4 | GPT-6 Astra (High) | 44.57 | #6 (GPT-6 Astra) |
| 5 | GPT-6 Astra (xHigh) | 43.67 | #6 (GPT-6 Astra) |
| 6 | GPT-6 Astra (Max) | 42.43 | #6 (GPT-6 Astra) |
| 7 | GPT-6.1 Sol (xHigh) | 42.37 | #10 (GPT-6.1 Sol) |
| 8 | GPT-6.1 Sol (Max) | 42.03 | #10 (GPT-6.1 Sol) |
| 9 | GPT-6 Astra (Medium) | 41.4 | #6 (GPT-6 Astra) |
| 10 | GPT-6.1 Sol (High) | 41 | #10 (GPT-6.1 Sol) |
| 11 | GPT-6 Astra (Low) | 40.3 | #6 (GPT-6 Astra) |
| 12 | GPT-6.1 Sol (Medium) | 40.17 | #10 (GPT-6.1 Sol) |
| 13 | Gemini 4 Carbon (Low) | 39.2 | #2 (Gemini 4 Carbon) |
| 14 | GPT-6.1 Sol (Low) | 38 | #10 (GPT-6.1 Sol) |
| 15 | Claude Opus 5 (Max) | 37.63 | #20 (Claude Opus 5) |
No result here: #1 Claude Fable 5.2, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=aa-omniscience-v1-1 · How It Works · Data refreshed daily, snapshot 2026-11-12.