HyperAI
Command Palette
Search for a command to run...
AutomationBench-AA
一项基准，衡量智能体在模拟 SaaS 应用环境中完成任务的比率，按每项任务在未违反防护规则的前提下完成的目标占比计分。
- 智能指数权重
- 5%
- 模型
- 150 当前，256 总共
- 中位数
- 46.0%
- 范围
- 0.2%–77.8%
| 排名 | 比较 | 模型 | 评分 | 成本 / 任务 | 时间 / 任务 | 输出 token / 任务 |
|---|---|---|---|---|---|---|
| 101 |  Ling-3.0-flash-VL InclusionAI | 15.7% | — | — | — | |
| 102 | 15.5% | — | — | — | ||
| 103 |  Nemotron 3.5 Super VL NVIDIA | 14.8% | $0.11 | 2m 1s | 31.3K | |
| 104 |  K2 Horizon 3.7B Institute of Foundation Models | 14.7% | — | — | — | |
| 105 |  Solar Pro 4 Upstage | 13.6% | — | — | — | |
| 106 |  Qwen3.8 27B (Non-reasoning) Alibaba | 12.4% | $0.24 | 4m 13s | 10.3K | |
| 107 |  GPT-6 Luna (Low) OpenAI | 12.0% | $0.0059 | 37.4s | 3.24K | |
| 108 | 9.1% | $0.014 | 52.6s | 4.74K | ||
| 109 | Ling-3.0-flash-Fin InclusionAI | 7.4% | — | — | — | |
| 110 | 6.9% | — | — | — | ||
| 111 | 6.8% | $0.091 | 3m 4s | 16.5K | ||
| 112 |  Mistral Medium 3.5 Mistral | 6.3% | $0.43 | 1m 52s | 15.7K | |
| 113 | 5.5% | — | — | — | ||
| 114 | Qwen3.6 35B A3B (Reasoning) Alibaba | 5.2% | — | — | — | |
| 115 |  Inkling (Xhigh) Thinking Machines | 5.0% | $0.22 | 1m 26s | 8.4K | |
| 116 |  Gemma 4 31B (Reasoning) Google | 4.9% | — | — | — | |
| 117 | Inkling Small Thinking Machines | 4.8% | $0.057 | 2m 5s | 8.94K | |
| 118 |  LongCat 2.0 LongCat | 4.5% | — | — | — | |
| 119 |  K-EXAONE 2.0 LG AI Research | 3.9% | — | — | 12.9K | |
| 120 | 3.0% | $0.13 | 29.7s | 5.61K | ||
| 121 |  A.X-K2 SK Telecom | 2.5% | — | — | — | |
| 122 |  Mercury 2.5 Inception | 2.4% | — | — | — | |
| 123 | 2.1% | $0.022 | 5m 19s | 30.7K | ||
| 124 | 1.9% | — | — | — | ||
| 125 |  Command A+ Cohere | 1.8% | $0 | 25.8s | 5.13K | |
| 126 |  MiniCPM5-2B OpenBMB | 1.8% | — | — | — | |
| 127 | 1.5% | — | — | — | ||
| 128 | North Mini Code Cohere | 1.5% | $0 | 28.9s | 4.91K | |
| 129 |  Trinity Large Thinking Arcee AI | 1.3% | — | — | — | |
| 130 | Qwen3 Coder Next Alibaba | 1.1% | — | — | — | |
| 131 | Qwen3.5 9B (Reasoning) Alibaba | 1.0% | — | — | — | |
| 132 | 1.0% | — | — | — | ||
| 133 | Mistral Small 4 (Reasoning) Mistral | 1.0% | $0.011 | 32.6s | 4.76K | |
| 134 | Nemotron 3.5 Lightning NVIDIA | 0.8% | $0.028 | 1m 19s | 19.2K | |
| 135 | Ring-2.6-1T InclusionAI | 0.7% | — | — | — | |
| 136 | Gemma 4 12B (Reasoning) Google | 0.7% | — | — | — | |
| 137 | Ministral 3 3B Mistral | 0.7% | — | — | — | |
| 138 | Ministral 3 14B Mistral | 0.6% | — | — | — | |
| 139 | Ministral 3 8B Mistral | 0.5% | — | — | — | |
| 140 | Gemma 4 E4B (Reasoning) Google | 0.5% | — | — | — | |
| 141 | 0.4% | — | — | 2.72K | ||
| 142 |  Celeris-1 Celeris | 0.4% | — | — | — | |
| 143 | 0.4% | — | — | 12K | ||
| 144 | Ling 3.0 Tiny InclusionAI | 0.3% | — | — | — | |
| 145 |  Llama 4 Maverick Meta | 0.2% | — | — | — | |
| 146 | K2 Horizon 0.9B Institute of Foundation Models | 0.2% | — | — | — | |
| 147 | gpt-oss-120b (High) OpenAI | 0.2% | $0.0033 | 13.5s | 2.18K | |
| 148 | gpt-oss-20b (High) OpenAI | 0.2% | — | — | — | |
| 149 | Llama 4 Scout Meta | 0.2% | — | — | — | |
| 150 | Magistral Small 1.2 Mistral | 0.2% | — | — | — |
- 102