Benchmarks · knowledge
AA-Omniscience v1.1 Accuracy
AA-Omniscience v1.1: correct answers divided by all questions.
28 models · 76 results · data as of 2026-10-29 · artificialanalysis.ai ↗
Leaderboard
Fable 5.1 max
All results
76 rows| # | Model | Effort | Score | Subscription $ / task | API $ / task |
|---|---|---|---|---|---|
| 1 | Fable 5.1 | max | 68.4% | $0.051 | $0.33 |
| 2 | Fable 5.1 | xhigh | 67.2% | $0.014 | $0.091 |
| 3 | Opus 5.5 | xhigh | 65.5% | $0.000 | $0.015 |
| 4 | Opus 5.5 | max | 65.5% | $0.003 | $0.19 |
| 5 | Opus 5.5 | high | 64.8% | $0.000 | $0.009 |
| 6 | Fable 5.1 | high | 64.7% | $0.004 | $0.023 |
| 7 | Opus 5.5 | medium | 63.9% | $0.000 | $0.008 |
| 8 | Opus 5.5 | low | 63.3% | $0.000 | $0.006 |
| 9 | Fable 5.1 | medium | 62.6% | $0.002 | $0.016 |
| 10 | GPT-6.1 Sol | max | 61.8% | $0.002 | $0.018 |
| 11 | GPT-6 Astra | max | 61.6% | $0.008 | $0.099 |
| 12 | GPT-6 Astra | high | 61.1% | $0.002 | $0.028 |
| 13 | GPT-6.1 Sol | xhigh | 61.1% | $0.001 | $0.009 |
| 14 | GPT-6 Astra | xhigh | 61.0% | $0.004 | $0.052 |
| 15 | GPT-6.1 Sol | high | 60.4% | $0.001 | $0.005 |
| 16 | GPT-6 Astra | medium | 59.6% | $0.001 | $0.011 |
| 17 | GPT-6.1 Sol | medium | 59.6% | $0.000 | $0.002 |
| 18 | Fable 5.1 | low | 58.7% | $0.001 | $0.008 |
| 19 | GPT-6.1 Sol | low | 58.6% | $0.000 | $0.001 |
| 20 | GPT-6 Astra | low | 58.6% | $0.001 | $0.007 |
| 21 | Gemini 4 Carbon | high | 58.3% | $0.25 | $0.25 |
| 22 | Sonnet 5.5 | max | 51.5% | $0.002 | $0.15 |
| 23 | Sonnet 5.5 | xhigh | 50.9% | $0.000 | $0.009 |
| 24 | Gemini 3.8 Flash | high | 50.5% | $0.001 | $0.014 |
| 25 | Sonnet 5.5 | high | 50.3% | $0.000 | $0.006 |
| 26 | Gemini 3.8 Flash | medium | 49.6% | $0.000 | $0.004 |
| 27 | Gemini 4 Argon | high | 48.3% | $0.006 | $0.018 |
| 28 | Gemini 3.8 Flash | low | 48.3% | ||
| 29 | GPT-6.1 Terra | xhigh | 48.0% | $0.008 | $0.008 |
| 30 | GPT-6.1 Terra | max | 47.6% | $0.043 | $0.043 |