HyperAI
Command Palette
Search for a command to run...
AA-Briefcase v1.1
장기 지평 지식 노동에서의 프런티어 에이전트 역량을 평가하는 비공개 평가로, 스프레드시트, 프레젠테이션, 메모 등의 산출물을 요구하는 현실적인 비즈니스 워크플로에서 에이전트를 시험합니다.
- 지능 지수 가중치
- 15%
- 모델
- 152 현재, 263 전체
- 중앙값
- 1186
- 범위
- 0–1816
| 순위 | 비교 | 모델 | 점수 | 비용 / 작업 | 시간 / 작업 | 출력 토큰 / 작업 |
|---|---|---|---|---|---|---|
| 51 |  Step 5 Preview StepFun | 1423 | $2.37 | 13m 55s | 120K | |
| 52 |  DeepSeek V4 Flash Vision (Max) DeepSeek | 1418 | — | — | — | |
| 53 | DeepSeek V4.1 Flash 1017 (High) DeepSeek | 1416 | $0.37 | 15m 8s | 129K | |
| 54 |  GPT-6.1 Terra (Max) OpenAI | 1403 | $0.81 | 13m 57s | 61.4K | |
| 55 |  Ling 3.1 Flash InclusionAI | 1397 | — | — | — | |
| 56 |  Qwen3.8 27B (Xhigh) Alibaba | 1391 | $3.25 | 51m 21s | 142K | |
| 57 | Qwen3.8 27B (Medium) Alibaba | 1372 | $3.15 | 50m 9s | 134K | |
| 58 |  Claude Haiku 5.5 (Medium) Anthropic | 1367 | $0.13 | 7m 18s | 98.6K | |
| 59 | GPT-6.1 Sol (Medium) OpenAI | 1360 | $0.46 | 5m 17s | 18.7K | |
| 60 |  Mistral Large 4 (High) Mistral | 1348 | $1.12 | 11m 51s | 83.4K | |
| 61 | GPT-6 Luna (Max) OpenAI | 1337 | $0.17 | 16m 46s | 110K | |
| 62 | GPT-6.1 Terra (Xhigh) OpenAI | 1333 | $0.41 | 6m 42s | 28.9K | |
| 63 |  K2 Horizon 375B A23B Institute of Foundation Models | 1292 | $0 | 9m 31s | 107K | |
| 64 | 1279 | $1.15 | 4m 7s | 26.7K | ||
| 65 | 1279 | $1.47 | 7m 9s | 74.1K | ||
| 66 | Qwen3.8 27B (Low) Alibaba | 1270 | $2.27 | 32m 47s | 98.6K | |
| 67 | 1268 | $0.80 | 5m 28s | 45.6K | ||
| 68 | GPT-6.1 Terra (High) OpenAI | 1264 | $0.28 | 4m 36s | 19.3K | |
| 69 | GPT-6 Astra (Low) OpenAI | 1256 | $1.44 | 4m 10s | 9.91K | |
| 70 | DeepSeek V4 Pro 0813 (Max) DeepSeek | 1253 | $1.00 | 22m 9s | 92.2K | |
| 71 | GPT-6 Luna (Xhigh) OpenAI | 1235 | $0.082 | 9m 16s | 57.3K | |
| 72 | 1226 | $0.22 | 3m 6s | 12.9K | ||
| 73 |  Gemini 3.8 Flash (High) Google | 1203 | $7.52 | 22m 22s | 154K | |
| 74 | GPT-6.1 Terra (Medium) OpenAI | 1190 | $0.18 | 3m 8s | 13K | |
| 75 | Mistral Large 4 (Medium) Mistral | 1188 | $0.44 | 5m 52s | 39.7K | |
| 76 | GPT-6 Luna (High) OpenAI | 1187 | $0.062 | 7m 18s | 42.5K | |
| 77 |  GLM-5.3 (Low) Z AI | 1185 | $0.73 | 9m 28s | 33.6K | |
| 78 | 1183 | $5.35 | 19m 10s | 129K | ||
| 79 | K2 Horizon MoVA 36B A4B Institute of Foundation Models | 1165 | — | — | — | |
| 80 |  Nanbeige4.3-33B Nanbeige | 1162 | — | — | 200K | |
| 81 |  Quasar 438B (Max, Based on GLM-5.2) Multiverse Computing | 1124 | — | — | — | |
| 82 | Claude Haiku 5.5 (Low) Anthropic | 1114 | $0.047 | 3m 4s | 40.2K | |
| 83 | GPT-6.1 Sol (Low) OpenAI | 1114 | $0.18 | 1m 59s | 6.71K | |
| 84 | GPT-6 Luna (Medium) OpenAI | 1096 | $0.033 | 3m 53s | 23.2K | |
| 85 |  Solar Pro 4 Upstage | 1093 | — | — | — | |
| 86 |  JT-4.1 Flash 236B A21B (Reasoning) China Mobile | 1092 | — | — | — | |
| 87 |  MiniMax-M3 MiniMax | 1089 | $0.94 | 10m 59s | 81.9K | |
| 88 | 1087 | — | — | — | ||
| 89 | Gemini 3.8 Flash (Low) Google | 1062 | — | — | — | |
| 90 | GPT-6.1 Terra (Low) OpenAI | 1031 | $0.085 | 1m 29s | 6.03K | |
| 91 | K2 Horizon 7B Institute of Foundation Models | 1014 | — | — | — | |
| 92 |  Apodex 1.1 Apodex | 1012 | $1.04 | 18m 22s | 157K | |
| 93 |  Nemotron 3.5 Super VL NVIDIA | 999 | $0.47 | 5m 45s | 89.4K | |
| 94 |  Motif 3 Motif Technologies | 992 | — | — | — | |
| 95 | Ling-3.0-flash-VL InclusionAI | 985 | — | — | — | |
| 96 |  Beam 1.0 Reflection | 976 | $0.20 | 1m 58s | 34.1K | |
| 97 | Ling-3.0-flash-Fin InclusionAI | 959 | — | — | — | |
| 98 |  Hy3 Tencent | 947 | — | — | — | |
| 99 | 940 | — | — | — | ||
| 100 | 928 | $0.36 | 7m 18s | 29.1K |
