Benchmarks · knowledge
AA-Omniscience v1.1 Law
AA-Omniscience v1.1 Index (-100..100) on the Law questions only: right answers minus made-up ones, abstaining scores 0.
28 models · 76 results · data as of 2026-10-29 · artificialanalysis.ai ↗
Leaderboard
Gemini 4 Carbon high
All results
76 rows| # | Model | Effort | AA-Omniscience v1.1 Law |
|---|---|---|---|
| 1 | Gemini 4 Carbon | high | 53.1 |
| 2 | Gemini 4 Argon | high | 41.1 |
| 3 | GPT-6 Astra | high | 38.9 |
| 4 | GPT-6 Astra | xhigh | 37.8 |
| 5 | Fable 5.1 | max | 36.4 |
| 6 | GPT-6.1 Sol | xhigh | 36.0 |
| 7 | GPT-6 Astra | max | 35.6 |
| 8 | Fable 5.1 | xhigh | 34.0 |
| 9 | GPT-6 Astra | medium | 33.3 |
| 10 | Opus 5.5 | max | 32.7 |
| 11 | GPT-6 Astra | low | 32.4 |
| 12 | GPT-6.1 Sol | high | 32.4 |
| 13 | GPT-6.1 Sol | max | 32.2 |
| 14 | GPT-6.1 Sol | medium | 32.0 |
| 15 | GPT-6.1 Sol | low | 28.4 |
| 16 | Fable 5.1 | high | 26.9 |
| 17 | Grok 4.7 | xhigh | 26.9 |
| 18 | Grok 4.7 | low | 26.7 |
| 19 | Opus 5.5 | xhigh | 25.8 |
| 20 | Fable 5.1 | medium | 25.6 |
| 21 | Gemini 3.8 Flash | medium | 25.6 |
| 22 | Fable 5.1 | low | 25.3 |
| 23 | Grok 4.7 | high | 24.0 |
| 24 | Gemini 3.8 Flash | high | 23.6 |
| 25 | Opus 5.5 | high | 22.2 |
| 26 | Opus 5.5 | medium | 20.7 |
| 27 | Opus 5.5 | low | 19.6 |
| 28 | GPT-6.1 Terra | max | 18.9 |
| 29 | GPT-6.1 Terra | high | 18.0 |
| 30 | Sonnet 5.5 | max | 17.3 |