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。 排序方式: 总成本 ↑.
169/169
筛选模型
没有模型匹配当前搜索和筛选条件。
| 排名 | 模型 | 公司 | 常识问答 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #167 | Nemotron 3 Nano Omni 30b A3b Reasoning none | NVIDIA | 3.0 | 3.5 | $0.000 | 0/1 | 0ms |
| #169 | LFM2-24B-A2B none | Liquid | 0.0 | 2.4 | $0.001 | 0/0 | 0ms |
| #143 | Ling-2.6-flash none | Inclusionai | 3.0 | 4.9 | $0.001 | 0/1 | 1.06s |
| #158 | Hy3 preview none | Tencent | 3.0 | 4.3 | $0.003 | 0/1 | 2.71s |
| #163 | Granite 4.1 8B none | IBM Granite | 3.0 | 4.0 | $0.003 | 0/1 | 306ms |
| #98 | Gemma 4 31B none | 3.0 | 6.1 | $0.004 | 0/1 | 1.25s | |
| #121 | Gemma 4 26B A4B none | 3.0 | 5.5 | $0.004 | 0/1 | 778ms | |
| #141 | GLM 4.7 Flash none | Z.ai | 3.0 | 4.9 | $0.004 | 0/1 | 692ms |
| #97 | Qwen3.5-Flash none | Qwen | 3.0 | 6.1 | $0.005 | 0/1 | 588ms |
| #147 | Ling-2.6-1T none | Inclusionai | 3.0 | 4.7 | $0.005 | 0/1 | 0ms |
| #135 | Qwen3.5-9B none | Qwen | 3.0 | 5.1 | $0.006 | 0/1 | 2.32s |
| #139 | GPT-4o-mini none | OpenAI | 3.0 | 5.0 | $0.006 | 0/1 | 794ms |
| #142 | Nemotron 3 Super none | NVIDIA | 3.0 | 4.9 | $0.007 | 0/1 | 8.94s |
| #134 | MiMo-V2.5 none | Xiaomi | 3.0 | 5.1 | $0.007 | 0/1 | 3.89s |
| #129 | Mistral Small 4 none | Mistral | 3.0 | 5.1 | $0.007 | 0/1 | 397ms |