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） |
|---|---|---|---|---|---|---|---|
| #46 | DeepSeek V4 Flash 0731 high | DeepSeek | 3.0 | 8.0 | $0.079 | 0/1 | 110.6s |
| #132 | Ring-2.6-1T medium | Inclusionai | 3.0 | 6.3 | $0.103 | 0/1 | 113.9s |
| #43 | Step 3.7 Flash medium | Stepfun | 3.0 | 8.0 | $0.515 | 0/1 | 114.0s |
| #249 | Step 3.5 Flash none | Stepfun | 3.0 | 2.3 | $0.020 | 0/1 | 114.1s |
| #112 | LongCat 2.0 low | Meituan | 3.0 | 6.7 | $0.391 | 0/1 | 122.1s |
| #106 | Qwen3.6 Flash medium | Qwen | 3.0 | 6.9 | $0.738 | 0/1 | 122.9s |
| #87 | Step 3.7 Flash low | Stepfun | 3.0 | 7.3 | $0.454 | 0/1 | 124.8s |
| #215 | Trinity Large Thinking high | Arcee AI | 3.0 | 4.8 | $0.632 | 0/1 | 125.1s |
| #45 | GLM 5.2 high | Z.ai | 3.0 | 8.0 | $0.466 | 0/1 | 127.8s |
| #88 | Kimi K2.6 medium | Moonshot AI | 3.0 | 7.2 | $0.746 | 0/1 | 130.3s |
| #213 | Ring-2.6-1T none | Inclusionai | 3.0 | 4.8 | $0.026 | 0/1 | 133.6s |
| #107 | Step 3.7 Flash high | Stepfun | 3.0 | 6.9 | $1.207 | 0/1 | 149.3s |
| #42 | Inkling high | Thinkingmachines | 3.0 | 8.0 | $1.006 | 0/1 | 153.6s |
| #243 | Qwen3.5-9B medium | Qwen | 3.0 | 3.8 | $0.036 | 0/1 | 177.0s |
| #143 | Qwen3.5-35B-A3B medium | Qwen | 3.0 | 6.2 | $0.837 | 0/1 | 177.4s |