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: 响应时间（平均） ↓.
250/250
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） |
|---|---|---|---|---|---|---|---|
| #70 | Kimi K2.7 Code medium | Moonshot AI | 3.0 | 7.5 | $0.686 | 0/1 | 341.8s |
| #164 | North Mini Code medium | Cohere | 3.0 | 5.9 | $0.000 | 0/1 | 305.0s |
| #39 | DeepSeek V4 Flash 0731 low | DeepSeek | 3.0 | 8.2 | $0.034 | 0/1 | 246.9s |
| #161 | Mimo V2 Omni medium | Xiaomi | 3.0 | 5.9 | $0.683 | 0/1 | 234.2s |
| #241 | Ling 3.0 Tiny low | Inclusionai | 3.0 | 3.8 | $0.000 | 0/1 | 213.5s |
| #240 | Ling 3.0 Tiny high | Inclusionai | 3.0 | 3.8 | $0.000 | 0/1 | 213.3s |
| #206 | Laguna S 2.1 low | Poolside | 3.0 | 5.0 | $0.082 | 0/1 | 202.5s |
| #226 | Laguna S 2.1 none | Poolside | 3.0 | 4.5 | $0.022 | 0/1 | 200.5s |
| #78 | LongCat 2.0 medium | Meituan | 3.0 | 7.4 | $0.478 | 0/1 | 191.2s |
| #117 | Gemma 4 26B A4B medium | 3.0 | 6.6 | $0.089 | 0/1 | 180.9s | |
| #143 | Qwen3.5-35B-A3B medium | Qwen | 3.0 | 6.2 | $0.837 | 0/1 | 177.4s |
| #243 | Qwen3.5-9B medium | Qwen | 3.0 | 3.8 | $0.036 | 0/1 | 177.0s |
| #42 | Inkling high | Thinkingmachines | 3.0 | 8.0 | $1.006 | 0/1 | 153.6s |
| #107 | Step 3.7 Flash high | Stepfun | 3.0 | 6.9 | $1.207 | 0/1 | 149.3s |
| #213 | Ring-2.6-1T none | Inclusionai | 3.0 | 4.8 | $0.026 | 0/1 | 133.6s |