Benchmarks · knowledge
AA-Omniscience v1.1
AA-Omniscience v1.1 Index (-100..100): knowledge accuracy minus a hallucination penalty. v1.1 drops saturated and public questions, adds new ones and revises ambiguous ones; scores run about 2 points below v1.
46 models · 99 results · data as of 2026-11-06 · artificialanalysis.ai ↗
Leaderboard
Gemini 4 Carbon high
Heavy line: best score at each price. Thin lines join one model's effort levels. Cost uses each model's median subscription plan, or API price with no plan data. 27 more models under All models in settings.
More from this benchmark
3 published measuresScore vs any published measure3 measures: sub-scores, splits, counts
32 more models under All models in settings.
Breakdown
darker is better within each column · click a column to sort| Model | |||
|---|---|---|---|
| Gemini 4 Carbon high | 6,236,419 | 70,218 | 35,629,296 |
| Opus 5.5 max | 515,923 | 195,322 | 27,793,033 |
| Fable 5.1 max | 516,515 | 186,054 | 19,329,356 |
| Gemini 4 Argon high | 411,694 | 103,091 | 2,547,401 |
| GPT-6 Astra high | 367,655 | 58,970 | 1,545,304 |
| GPT-6.1 Sol xhigh | 367,655 | 57,858 | 2,621,560 |
| Opus 5 max | 510,023 | 351,709 | 2,753,012 |
| Grok 4.7 xhigh | 2,377,216 | 15,341 | 13,359,778 |
| Sonnet 5.5 max | 516,038 | 216,035 | 45,227,159 |
| Kimi K3.1 max | 626,637 | 109,287 | 12,641,505 |
| GPT-6.1 Terra max | 367,459 | 48,950 | 25,386,348 |
| Muse Spark Open xhigh | 764,612 | 153,576 | 6,240,557 |
| Muse Wonder (Max) | 361,438 | 40,815 | 7,013,480 |
| Grok 4.6 xhigh | 2,259,461 | 14,478 | 6,456,398 |
| Muse Spark 1.3 xhigh | 362,331 | 38,955 | 9,963,233 |
| Gemini 3.8 Flash medium | 358,836 | 31,303 | 2,921,304 |
| GPT-6 Sol max | 367,656 | 47,246 | 6,970,887 |
| Inkling 2 Small | 419,150 | 472,181 | 3,295,875 |
| Haiku 5.5 max | 515,866 | 205,357 | 35,770,312 |
| Qwen 3.8 2.4T-A95B | 507,360 | 36,202 | 4,772,166 |
| Gemini 3.5 Flash-Lite high | 358,836 | 39,866 | 3,387,780 |
| GLM 5.3 max | 377,753 | 253,325 | 13,617,030 |
| Hy4 | 400,186 | 45,117 | 48,123,059 |
| Mistral Large 4 high | 390,859 | 148,964 | 9,142,902 |
| Nemotron 3 Ultra max | 391,443 | 186,950 | 2,071,839 |
All results
99 rows| # | Model | Effort | AA-Omniscience v1.1 | Subscription $ / task | API $ / task |
|---|---|---|---|---|---|
| 1 | Gemini 4 Carbon | high | 53.5 | $0.088 | $0.25 |
| 2 | Opus 5.5 | max | 48.1 | $0.003 | $0.19 |
| 3 | Gemini 4 Carbon | medium | 46.8 | $0.009 | $0.025 |
| 4 | Fable 5.1 | max | 46.3 | $0.051 | $0.33 |
| 5 | Gemini 4 Argon | high | 46.1 | $0.013 | $0.018 |
| 6 | GPT-6 Astra | high | 44.6 | $0.001 | $0.028 |
| 7 | Fable 5.1 | xhigh | 44.3 | $0.014 | $0.091 |
| 8 | GPT-6 Astra | xhigh | 43.7 | $0.002 | $0.052 |
| 9 | Opus 5.5 | xhigh | 43.1 | $0.000 | $0.015 |
| 10 | GPT-6 Astra | max | 42.4 | $0.004 | $0.099 |
| 11 | Opus 5.5 | high | 42.4 | $0.000 | $0.009 |
| 12 | GPT-6.1 Sol | xhigh | 42.4 | $0.001 | $0.009 |
| 13 | GPT-6.1 Sol | max | 42.0 | $0.001 | $0.018 |
| 14 | GPT-6 Astra | medium | 41.4 | $0.000 | $0.011 |
| 15 | GPT-6.1 Sol | high | 41.0 | $0.000 | $0.005 |
| 16 | GPT-6 Astra | low | 40.3 | $0.000 | $0.007 |
| 17 | GPT-6.1 Sol | medium | 40.2 | $0.000 | $0.002 |
| 18 | Fable 5.1 | high | 39.9 | $0.004 | $0.023 |
| 19 | Opus 5.5 | medium | 39.8 | $0.000 | $0.008 |
| 20 | Gemini 4 Carbon | low | 39.2 | $0.001 | $0.002 |
| 21 | Opus 5.5 | low | 39.0 | $0.000 | $0.006 |
| 22 | GPT-6.1 Sol | low | 38.0 | $0.000 | $0.001 |
| 23 | Opus 5 | max | 37.6 | $0.000 | $0.027 |
| 24 | Fable 5.1 | medium | 36.4 | $0.002 | $0.016 |
| 25 | Fable 5.1 | low | 33.9 | $0.001 | $0.008 |
| 26 | Grok 4.7 | xhigh | 31.2 | $0.003 | $0.028 |
| 27 | Sonnet 5.5 | max | 30.5 | $0.002 | $0.15 |
| 28 | Grok 4.7 | high | 30.0 | $0.002 | $0.022 |
| 29 | Kimi K3.1 | max | 29.9 | $0.043 | $0.043 |
| 30 | GPT-6.1 Terra | max | 29.6 | $0.002 | $0.043 |