HyperAI
Command Palette
Search for a command to run...
GDPval-AA v2.1
GDPval-AA v2.1 是面向 OpenAI GDPval 数据集的评测框架。它在 44 种职业和 9 个主要行业中测试 AI 模型的真实工作任务。模型通过 Stirrup 在智能体循环中获得 shell 访问和网页浏览能力来解题，Elo 评分来自盲评两两对比。
- 模型
- 172 当前，315 总共
- 中位数
- 1109
- 范围
- -402–1866
| 排名 | 比较 | 模型 | 评分 |
|---|---|---|---|
| 101 | 979 | ||
| 102 |  Solar Open2 250B Upstage | 978 | |
| 103 |  A.X-K2 SK Telecom | 968 | |
| 104 |  Qwen3.6 35B A3B (Reasoning) Alibaba | 899 | |
| 105 |  K2 Horizon 3.7B Institute of Foundation Models | 889 | |
| 106 |  LongCat 2.0 LongCat | 877 | |
| 107 | 854 | ||
| 108 | 822 | ||
| 109 |  K-EXAONE 2.0 LG AI Research | 816 | |
| 110 | 801 | ||
| 111 |  Gemini 3.1 Pro Preview Google | 799 | |
| 112 | 792 | ||
| 113 | Qwen3.7 Plus Alibaba | 775 | |
| 114 |  Mistral Medium 3.5 Mistral | 769 | |
| 115 |  Ring-2.6-1T InclusionAI | 753 | |
| 116 |  KAT Coder Pro V2 KwaiKAT | 742 | |
| 117 | 716 | ||
| 118 |  MiniCPM5-2B OpenBMB | 715 | |
| 119 |  Nemotron 3.5 Lightning NVIDIA | 646 | |
| 120 | Gemma 4 31B (Reasoning) Google | 627 | |
| 121 |  gpt-oss-120b (High) OpenAI | 616 | |
| 122 | 583 | ||
| 123 | 573 | ||
| 124 | Ling 3.0 Tiny InclusionAI | 568 | |
| 125 | 555 | ||
| 126 |  Command A+ Cohere | 522 | |
| 127 | Qwen3 Coder Next Alibaba | 521 | |
| 128 | 516 | ||
| 129 | 499 | ||
| 130 |  Mercury 2.5 Inception | 482 | |
| 131 | 477 | ||
| 132 | EXAONE 4.5 33B (Reasoning) LG AI Research | 474 | |
| 133 |  HyperNova 60B 2605 (High, Based on gpt-oss-120b) Multiverse Computing | 449 | |
| 134 | 444 | ||
| 135 | Gemma 4 12B (Reasoning) Google | 435 | |
| 136 | Qwen3.5 9B (Reasoning) Alibaba | 427 | |
| 137 |  Nova 2.0 Lite (High) Amazon | 374 | |
| 138 | Mistral Small 4 (Reasoning) Mistral | 370 | |
| 139 | gpt-oss-20b (High) OpenAI | 347 | |
| 140 |  Trinity Large Thinking Arcee AI | 344 | |
| 141 | 339 | ||
| 142 | DiffusionGemma 26B A4B Google | 329 | |
| 143 | North Mini Code Cohere | 319 | |
| 144 |  Celeris-1 Celeris | 309 | |
| 145 | 272 | ||
| 146 | 262 | ||
| 147 | Ministral 3 14B Mistral | 255 | |
| 148 | 237 | ||
| 149 | Ministral 3 8B Mistral | 221 | |
| 150 | 209 |
