HyperAI
Command Palette
Search for a command to run...
AA-Briefcase v1.1
一项私有评测，考察前沿智能体在长周期知识工作中的能力，让智能体处理真实商业流程，并要求产出电子表格、演示文稿和备忘录等交付物。
- 智能指数权重
- 15%
- 模型
- 152 当前，263 总共
- 中位数
- 1186
- 范围
- 0–1816
| 排名 | 比较 | 模型 | 评分 | 成本 / 任务 | 时间 / 任务 | 输出 token / 任务 |
|---|---|---|---|---|---|---|
| 101 |  Qwen3.7 Plus Alibaba | 915 | — | — | — | |
| 102 |  Inkling Small Thinking Machines | 913 | $0.12 | 6m 45s | 29K | |
| 103 | 912 | — | — | — | ||
| 104 | 903 | $0.021 | 1m 41s | 9.08K | ||
| 105 | Qwen3.8 27B (Non-reasoning) Alibaba | 901 | $8.99 | 33m 22s | 81.4K | |
| 106 | 877 | $0.81 | 4m 12s | 47.5K | ||
| 107 |  GPT-5.3 Codex (Xhigh) OpenAI | 868 | — | — | — | |
| 108 |  Solar Mini 4 Upstage | 868 | — | — | — | |
| 109 |  Kimi K2.7 Code Kimi | 858 | — | — | — | |
| 110 | Inkling (Xhigh) Thinking Machines | 833 | $1.40 | 8m 56s | 52.2K | |
| 111 |  K2 Horizon 3.7B Institute of Foundation Models | 793 | — | — | — | |
| 112 | GPT-6 Luna (Low) OpenAI | 740 | $0.0061 | 49.8s | 4.31K | |
| 113 |  LongCat 2.0 LongCat | 740 | — | — | — | |
| 114 |  A.X-K2 SK Telecom | 739 | — | — | — | |
| 115 | Qwen3.6 35B A3B (Reasoning) Alibaba | 713 | — | — | — | |
| 116 |  Ring-2.6-1T InclusionAI | 658 | — | — | — | |
| 117 |  Gemini 3.5 Flash-Lite Google | 651 | $0.15 | 1m 14s | 23K | |
| 118 |  K-EXAONE 2.0 LG AI Research | 651 | — | — | 66.7K | |
| 119 | 563 | — | — | — | ||
| 120 |  Mistral Medium 3.5 Mistral | 523 | $0.67 | 4m 2s | 34K | |
| 121 |  Nemotron 3.5 Lightning NVIDIA | 507 | $0.31 | 5m 29s | 80K | |
| 122 | 497 | — | — | — | ||
| 123 | 478 | $0.077 | 2m 31s | 13.5K | ||
| 124 | Ling 3.0 Tiny InclusionAI | 476 | — | — | — | |
| 125 | Gemini 3.1 Pro Preview Google | 457 | — | — | — | |
| 126 |  MiniCPM5-2B OpenBMB | 423 | — | — | — | |
| 127 | Qwen3 Coder Next Alibaba | 404 | — | — | — | |
| 128 | 395 | — | — | — | ||
| 129 |  Mercury 2.5 Inception | 378 | — | — | — | |
| 130 | Gemma 4 31B (Reasoning) Google | 369 | — | — | — | |
| 131 |  Command A+ Cohere | 356 | $0 | 2m 15s | 26.9K | |
| 132 | Qwen3.5 9B (Reasoning) Alibaba | 341 | — | — | — | |
| 133 | 316 | — | — | — | ||
| 134 | 310 | $0.088 | 16m 39s | 96.3K | ||
| 135 |  Trinity Large Thinking Arcee AI | 256 | — | — | — | |
| 136 | Mistral Small 4 (Reasoning) Mistral | 241 | $0.022 | 1m 35s | 13.9K | |
| 137 |  HyperNova 60B 2605 (High, Based on gpt-oss-120b) Multiverse Computing | 232 | — | — | — | |
| 138 | North Mini Code Cohere | 212 | $0 | 3m 3s | 31K | |
| 139 |  Celeris-1 Celeris | 152 | — | — | — | |
| 140 | Ministral 3 14B Mistral | 132 | — | — | — | |
| 141 | 99 | — | — | 29.9K | ||
| 142 | Ministral 3 8B Mistral | 78 | — | — | — | |
| 143 | 78 | — | — | — | ||
| 144 | K2 Think V2 Institute of Foundation Models | 8 | — | — | — | |
| 145 | Gemma 4 E4B (Reasoning) Google | 0 | — | — | — | |
| 146 | gpt-oss-120b (High) OpenAI | 0 | $0.57 | 10m 5s | 97.7K | |
| 147 | gpt-oss-20b (High) OpenAI | 0 | — | — | — | |
| 148 | K2 Horizon 0.9B Institute of Foundation Models | 0 | — | — | — | |
| 149 |  Llama 4 Maverick Meta | 0 | — | — | — | |
| 150 | Llama 4 Scout Meta | 0 | — | — | — |
