AI BENCHY 分类
常识问答 排名
看看哪些 AI 模型在 常识问答 上表现最好，哪些更稳定，以及差距主要出现在哪里。
失败原因
| 排名 | 模型 | 公司 | 常识问答 得分 | 分数 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|
| #127 | GPT-4o-mini none | OpenAI | 3.0 | 4.9 | 0/1 | 794ms |
| #128 | MiMo-V2.5 none | Xiaomi | 3.0 | 4.9 | 0/1 | 3.89s |
| #129 | Qwen3 Coder Next medium | Qwen | 3.0 | 4.8 | 0/1 | 399ms |
| #130 | Trinity Large Preview none | Arcee AI | 3.0 | 4.8 | 0/1 | 777ms |
| #131 | Mercury 2 none | Inception | 3.0 | 4.7 | 0/1 | 548ms |
| #132 | Qwen3.5-9B none | Qwen | 3.0 | 4.7 | 0/1 | 2.32s |
| #133 | HY3 Preview none | Tencent | 3.0 | 4.6 | 0/1 | 2.71s |
| #135 | GPT-5.4 Nano none | OpenAI | 3.0 | 4.5 | 0/1 | 773ms |
| #136 | GLM 4.7 Flash medium | Z.ai | 3.0 | 4.5 | 0/1 | 11.1s |
| #137 | MiMo-V2-Flash none | Xiaomi | 3.0 | 4.5 | 0/1 | 1.82s |
| #139 | Grok 4.1 Fast none | X AI | 3.0 | 4.4 | 0/1 | 731ms |
| #140 | Qwen3.5-9B medium | Qwen | 3.0 | 4.3 | 0/1 | 177.0s |
| #142 | Granite 4.1 8B none | IBM Granite | 3.0 | 4.1 | 0/1 | 306ms |
| #4 | GPT-5.5 medium | OpenAI | 2.8 | 8.9 | 0/1 | 37.9s |
| #13 | GPT-5.3-Codex medium | OpenAI | 2.8 | 8.2 | 0/1 | 14.4s |