HyperAI
Command Palette
Search for a command to run...
AA-Omniscience v1.1
一项基准，衡量模型在多个具有经济价值的领域中事实回忆与幻觉的情况。
- 类别
- 通用
- 智能指数权重
- 15%
- 模型
- 102 当前，117 总共
- 中位数
- 7.1
- 范围
- -71.2–66.8
| 排名 | 比较 | 模型 | 评分 | 成本 / 任务 | 时间 / 任务 | 输出 token / 任务 |
|---|---|---|---|---|---|---|
| 1 | 66.8 | $0.22 | 52.9s | 5.44K | ||
| 2 | 64.8 | $0.033 | 7.6s | 781 | ||
| 3 | 64.0 | $0.02 | 4.9s | 455 | ||
| 4 | 63.5 | $0.015 | 3.8s | 349 | ||
| 5 | 62.9 | $0.014 | 3.3s | 309 | ||
| 6 |  Gemini 4 Carbon (High) Google | 53.5 | $0.25 | 2m 25s | 11.9K | |
| 7 | 48.1 | $0.19 | 1m 20s | 9.33K | ||
| 8 | Gemini 4 Carbon (Medium) Google | 46.8 | $0.025 | 16.6s | 1.23K | |
| 9 | Gemini 4 Argon (High) Google | 46.1 | $0.018 | 13.0s | 883 | |
| 10 |  GPT-6 Astra (High) OpenAI | 44.6 | $0.028 | 13.6s | 535 | |
| 11 | GPT-6 Astra (Xhigh) OpenAI | 43.7 | $0.052 | 26.0s | 1.01K | |
| 12 | 43.1 | $0.015 | 6.5s | 703 | ||
| 13 | GPT-6 Astra (Max) OpenAI | 42.4 | $0.099 | 51.9s | 1.95K | |
| 14 | 42.4 | $0.0093 | 4.1s | 430 | ||
| 15 | GPT-6.1 Sol (Xhigh) OpenAI | 42.4 | $0.0092 | 16.0s | 893 | |
| 16 | GPT-6.1 Sol (Max) OpenAI | 42.0 | $0.018 | 32.1s | 1.81K | |
| 17 | GPT-6 Astra (Medium) OpenAI | 41.4 | $0.011 | 4.6s | 194 | |
| 18 | GPT-6.1 Sol (High) OpenAI | 41.0 | $0.0049 | 8.2s | 469 | |
| 19 | GPT-6 Astra (Low) OpenAI | 40.3 | $0.007 | 2.9s | 115 | |
| 20 | GPT-6.1 Sol (Medium) OpenAI | 40.2 | $0.0022 | 3.2s | 191 | |
| 21 | 39.8 | $0.0082 | 3.6s | 377 | ||
| 22 | Gemini 4 Carbon (Low) Google | 39.2 | $0.0015 | 0.71s | 45.5 | |
| 23 | 39.0 | $0.0063 | 2.6s | 279 | ||
| 24 | GPT-6.1 Sol (Low) OpenAI | 38.0 | $0.0015 | 2.2s | 125 | |
| 25 |  Grok 4.7 (Xhigh) SpaceXAI | 31.2 | $0.028 | 1m 10s | 4.46K | |
| 26 | 30.6 | — | — | 3.3K | ||
| 27 | 30.5 | $0.15 | 1m 39s | 15.1K | ||
| 28 | Grok 4.7 (High) SpaceXAI | 30.0 | $0.022 | 46.8s | 3.15K | |
| 29 |  Kimi K3.1 Pro Kimi | 29.9 | $0.043 | 2m 11s | 4.25K | |
| 30 | GPT-6.1 Terra (Max) OpenAI | 29.6 | $0.043 | 1m 56s | 8.48K | |
| 31 | GPT-6.1 Terra (Xhigh) OpenAI | 28.9 | $0.0079 | 21.8s | 1.56K | |
| 32 | GPT-6.1 Terra (High) OpenAI | 27.8 | $0.003 | 8.1s | 566 | |
| 33 | Grok 4.7 (Low) SpaceXAI | 27.4 | $0.01 | 18.9s | 1.22K | |
| 34 | GPT-6.1 Terra (Medium) OpenAI | 26.6 | $0.0016 | 4.3s | 300 | |
| 35 | 25.8 | $0.0094 | 12.3s | 2.13K | ||
| 36 | 25.1 | $0.048 | 19.3s | 2.35K | ||
| 37 | 24.5 | $0.03 | 12.1s | 1.46K | ||
| 38 | 23.7 | $0.0038 | 8.8s | 984 | ||
| 39 | Gemini 3.8 Flash (High) Google | 23.3 | $0.014 | 31.4s | 3.61K | |
| 40 | GPT-6.1 Terra (Low) OpenAI | 22.9 | $0.00079 | 2.0s | 133 | |
| 41 | 20.6 | $0.0088 | 6.1s | 848 | ||
| 42 | 20.3 | $0.0029 | 1.8s | 256 | ||
| 43 | 18.7 | $0.0057 | 3.8s | 533 | ||
| 44 | 18.6 | $0.0031 | 2.0s | 277 | ||
| 45 |  Step 5 Preview StepFun | 16.4 | $0.015 | 37.5s | 5.41K | |
| 46 |  Inkling 2 Small Thinking Machines | 16.1 | $0.0013 | 9.8s | 1.26K | |
| 47 |  Claude Haiku 5.5 (Max) Anthropic | 12.3 | $0.006 | 47.2s | 12K | |
| 48 |  Qwen3.8 Max (0902) Alibaba | 10.5 | $0.0083 | 26.4s | 1.35K | |
| 49 | Claude Haiku 5.5 (Xhigh) Anthropic | 7.8 | $0.00069 | 5.7s | 1.35K | |
| 50 | 7.7 | $0.0011 | 4.5s | 2.08K |
- Anthropic
- 评分
- 66.8
- 成本 / 任务
- $0.22
- 时间 / 任务
- 52.9s
- 输出 token / 任务
- 5.44K
- Anthropic
- 评分
- 64.8
- 成本 / 任务
- $0.033
- 时间 / 任务
- 7.6s
- 输出 token / 任务
- 781
- Anthropic
- 评分
- 63.5
- 成本 / 任务
- $0.015
- 时间 / 任务
- 3.8s
- 输出 token / 任务
- 349
- Anthropic
- 评分
- 48.1
- 成本 / 任务
- $0.19
- 时间 / 任务
- 1m 20s
- 输出 token / 任务
- 9.33K
- Anthropic
- 评分
- 43.1
- 成本 / 任务
- $0.015
- 时间 / 任务
- 6.5s
- 输出 token / 任务
- 703
- Anthropic
- 评分
- 42.4
- 成本 / 任务
- $0.0093
- 时间 / 任务
- 4.1s
- 输出 token / 任务
- 430
- Anthropic
- 评分
- 39.8
- 成本 / 任务
- $0.0082
- 时间 / 任务
- 3.6s
- 输出 token / 任务
- 377
- Anthropic
- 评分
- 39.0
- 成本 / 任务
- $0.0063
- 时间 / 任务
- 2.6s
- 输出 token / 任务
- 279
- Anthropic
- 评分
- 30.5
- 成本 / 任务
- $0.15
- 时间 / 任务
- 1m 39s
- 输出 token / 任务
- 15.1K
- Anthropic
- 评分
- 20.6
- 成本 / 任务
- $0.0088
- 时间 / 任务
- 6.1s
- 输出 token / 任务
- 848
- Anthropic
- 评分
- 20.3
- 成本 / 任务
- $0.0029
- 时间 / 任务
- 1.8s
- 输出 token / 任务
- 256
- Anthropic
- 评分
- 18.7
- 成本 / 任务
- $0.0057
- 时间 / 任务
- 3.8s
- 输出 token / 任务
- 533
- Anthropic
- 评分
- 18.6
- 成本 / 任务
- $0.0031
- 时间 / 任务
- 2.0s
- 输出 token / 任务
- 277