HyperAI
Command Palette
Search for a command to run...
AA-Omniscience v1.1
경제적으로 중요한 다양한 영역에서 사실 회상과 환각을 측정하는 벤치마크입니다.
- 카테고리
- 일반
- 지능 지수 가중치
- 15%
- 모델
- 102 현재, 117 전체
- 중앙값
- 7.1
- 범위
- -71.2–66.8
| 순위 | 비교 | 모델 | 점수 | 비용 / 작업 | 시간 / 작업 | 출력 토큰 / 작업 |
|---|---|---|---|---|---|---|
| 51 |  Muse Ember (Max) Meta | 7.4 | $0.0015 | 6.4s | 2.9K | |
| 52 |  Gemini 3.5 Flash-Lite Google | 6.9 | $0.0029 | 3.7s | 1.14K | |
| 53 |  GLM-5.3 (Max) Z AI | 6.0 | $0.021 | 1m 7s | 4.62K | |
| 54 |  Tencent Hy4 Tencent | 5.4 | $0.04 | — | 16.1K | |
| 55 |  Claude Haiku 5.5 (High) Anthropic | 5.3 | $0.0004 | 3.4s | 769 | |
| 56 |  Mistral Large 4 (High) Mistral | 5.1 | $0.0066 | 26.4s | 3.1K | |
| 57 | Claude Haiku 5.5 (Medium) Anthropic | 4.2 | $0.00031 | 2.6s | 593 | |
| 58 | 3.4 | $0.0021 | 4.0s | 753 | ||
| 59 | Mistral Large 4 (Medium) Mistral | 3.3 | $0.0028 | 11.5s | 1.3K | |
| 60 |  Beam 1.0 Reflection | 2.3 | $0.0016 | 4.5s | 1.29K | |
| 61 | Claude Haiku 5.5 (Low) Anthropic | 2.2 | $0.00025 | 2.2s | 472 | |
| 62 | 2.1 | $0.00011 | 0.48s | 60.5 | ||
| 63 |  DeepSeek V4.1 Flash 1017 (High) DeepSeek | 1.5 | $0.0015 | 8.6s | 1.22K | |
| 64 | DeepSeek V4.1 Flash 1017 (Max) DeepSeek | 0.9 | $0.0018 | 10.7s | 1.47K | |
| 65 | GLM-5.3-Flash Z AI | 0.7 | $0.0016 | 1m 5s | 3.22K | |
| 66 |  Ling 3.1 Flash 1019 InclusionAI | -0.1 | $0.01 | — | 11.5K | |
| 67 |  Inkling (Xhigh) Thinking Machines | -1.5 | $0.018 | 45.5s | 4.43K | |
| 68 |  Command A+ Cohere | -2.7 | $0 | 11.6s | 2.32K | |
| 69 |  Nemotron 3.5 Super VL NVIDIA | -2.9 | $0.0018 | 14.0s | 3.64K | |
| 70 |  Nanbeige4.3-33B Nanbeige | -4.4 | — | — | 1.31K | |
| 71 |  MiMo-V2.6-Pro Xiaomi | -4.5 | $0.0056 | 1m 52s | 6.32K | |
| 72 | -5.0 | $0.00019 | 0.2s | 14 | ||
| 73 |  K2 Horizon 375B A23B Institute of Foundation Models | -5.0 | $0 | 12.5s | 2.36K | |
| 74 |  MiniMax-M3 MiniMax | -5.5 | $0.0061 | 40.5s | 5.04K | |
| 75 | DeepSeek V4 Pro 0813 (Max) DeepSeek | -6.4 | $0.012 | 42.1s | 2.92K | |
| 76 |  Qwen3.8 27B (Xhigh) Alibaba | -6.4 | $0.01 | 1m 15s | 3.46K | |
| 77 | MiniMax-M3.1-Flash MiniMax | -6.4 | $0.0032 | 32.5s | 5.19K | |
| 78 | Qwen3.8 27B (Non-reasoning) Alibaba | -7.3 | $0.00014 | 0.59s | 24 | |
| 79 |  GPT-6 Luna (Max) OpenAI | -8.3 | $0.0023 | 42.7s | 4.66K | |
| 80 | Inkling Small Thinking Machines | -9.5 | $0.0051 | 58.8s | 4.21K | |
| 81 | MiMo-V2.6-Flash Xiaomi | -10.8 | $0.0034 | 5m 39s | 11.9K | |
| 82 | GLM-5.3 (Low) Z AI | -11.2 | $0.00091 | 2.8s | 167 | |
| 83 |  Agnes 2.5 Pro Theta Sapiens AI | -11.2 | $0.00067 | 11.1s | 2.15K | |
| 84 |  K-EXAONE 2.0 LG AI Research | -11.5 | — | — | 1.53K | |
| 85 | GPT-6 Luna (High) OpenAI | -12.8 | $0.00057 | 11.6s | 1.12K | |
| 86 | GPT-6 Luna (Xhigh) OpenAI | -13.0 | $0.00089 | 16.9s | 1.75K | |
| 87 | GPT-6 Luna (Medium) OpenAI | -13.6 | $0.00036 | 7.0s | 698 | |
| 88 | Nemotron 3.5 Lightning NVIDIA | -15.7 | $0.0006 | 12.1s | 2.94K | |
| 89 | -16.7 | $0.0011 | 46.0s | 4.43K | ||
| 90 | GPT-6 Luna (Low) OpenAI | -18.1 | $0.00018 | 3.8s | 332 | |
| 91 | -18.3 | — | — | 5.31K | ||
| 92 | -19.1 | $0.00096 | 3.1s | 205 | ||
| 93 | Qwen3.8 27B (Low) Alibaba | -21.5 | $0.0014 | 9.0s | 451 | |
| 94 | -25.8 | $0.000021 | 0.19s | 17.5 | ||
| 95 |  Apodex 1.1 Apodex | -27.9 | $0.015 | 35.5s | 5.04K | |
| 96 | Mistral Small 4 (Reasoning) Mistral | -31.0 | $0.00043 | 4.7s | 679 | |
| 97 | -32.2 | $0.0024 | 22.0s | 1.97K | ||
| 98 | Qwen3.8 27B (Medium) Alibaba | -35.9 | $0.008 | 59.5s | 2.66K | |
| 99 | Mistral Medium 3.5 Mistral | -38.7 | $0.014 | 13.0s | 1.82K | |
| 100 | gpt-oss-120b (High) OpenAI | -46.4 | $0.0027 | 27.2s | 4.39K |
