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: 测试正确 ↓.
364/364
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） |
|---|---|---|---|---|---|---|---|
| #271 | Hy4 preview low | Tencent | 3.0 | 5.6 | $1.745 | 0/1 | 597.4s |
| #272 | Qwen3.6 27B none | Qwen | 3.0 | 5.5 | $0.075 | 0/1 | 4.03s |
| #273 | Hy3 preview low | Tencent | 3.0 | 5.5 | $0.042 | 0/1 | 41.7s |
| #274 | Qwen3.8 27B none | Qwen | 3.0 | 5.5 | ~$0.006 | 0/1 | 703ms |
| #275 | Mimo V2 Omni none | Xiaomi | 3.0 | 5.5 | $0.021 | 0/1 | 1.30s |
| #276 | MiMo-V2.6-Flash none | Xiaomi | 3.0 | 5.4 | $0.037 | 0/1 | 55.1s |
| #277 | DeepSeek V4 Flash 0423 none | DeepSeek | 3.0 | 5.4 | $0.040 | 0/1 | 3.07s |
| #278 | DeepSeek V4.1 Flash none | DeepSeek | 3.0 | 5.4 | $0.135 | 0/1 | 1.32s |
| #279 | Laguna S 2.1 medium | Poolside | 3.0 | 5.4 | $0.053 | 0/1 | 7.11s |
| #280 | KAT-Coder-Air V2.5 low | Kwaipilot | 3.0 | 5.4 | $0.046 | 0/1 | 20.0s |
| #281 | GPT-5.6 Luna none | OpenAI | 3.0 | 5.4 | $0.029 | 0/1 | 651ms |
| #282 | MiMo-V2.5-Pro none | Xiaomi | 3.0 | 5.4 | $0.068 | 0/1 | 1.89s |
| #283 | Kimi K2.5 none | Moonshot AI | 3.0 | 5.4 | $0.101 | 0/1 | 3.90s |
| #284 | DeepSeek V4 Flash 0731 none | DeepSeek | 3.0 | 5.4 | $0.021 | 0/1 | 1.85s |
| #285 | Laguna S 2.1 high | Poolside | 3.0 | 5.4 | $0.114 | 0/1 | 6.94s |