Benchmarks · knowledge
AA-Omniscience v1.1 Public set
AA-Omniscience v1.1 Index on AA-Omniscience-Public-v1.1, the open subset AA released on Hugging Face, recalibrated to match the private set.
28 models · 76 results · data as of 2026-10-29 · artificialanalysis.ai ↗
Leaderboard
Gemini 4 Carbon high
All results
76 rows| # | Model | Effort | Score |
|---|---|---|---|
| 1 | Gemini 4 Carbon | high | 55.0 |
| 2 | Opus 5.5 | max | 49.0 |
| 3 | Fable 5.1 | max | 47.7 |
| 4 | Gemini 4 Argon | high | 46.7 |
| 5 | GPT-6 Astra | high | 46.0 |
| 6 | Opus 5.5 | xhigh | 45.3 |
| 7 | GPT-6 Astra | medium | 45.3 |
| 8 | Fable 5.1 | xhigh | 45.0 |
| 9 | GPT-6 Astra | xhigh | 44.3 |
| 10 | GPT-6 Astra | max | 43.7 |
| 11 | GPT-6.1 Sol | xhigh | 43.7 |
| 12 | Opus 5.5 | high | 42.3 |
| 13 | GPT-6.1 Sol | max | 42.0 |
| 14 | Opus 5.5 | low | 41.3 |
| 15 | GPT-6.1 Sol | high | 41.3 |
| 16 | Opus 5.5 | medium | 39.7 |
| 17 | Fable 5.1 | high | 38.3 |
| 18 | GPT-6.1 Sol | medium | 38.3 |
| 19 | GPT-6.1 Sol | low | 38.0 |
| 20 | GPT-6 Astra | low | 37.3 |
| 21 | Fable 5.1 | low | 36.0 |
| 22 | Fable 5.1 | medium | 35.3 |
| 23 | Grok 4.7 | xhigh | 31.3 |
| 24 | GPT-6.1 Terra | max | 31.0 |
| 25 | GPT-6.1 Terra | medium | 30.3 |
| 26 | Grok 4.7 | high | 30.0 |
| 27 | GPT-6.1 Terra | xhigh | 29.7 |
| 28 | GPT-6.1 Terra | high | 28.3 |
| 29 | Sonnet 5.5 | max | 28.0 |
| 30 | Muse Spark 1.3 | max | 24.3 |