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: 测试正确 ↓.
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） |
|---|---|---|---|---|---|---|---|
| #106 | Qwen3.5 Plus 2026-02-15 none | Qwen | 3.0 | 5.8 | $0.016 | 0/1 | 1.11s |
| #107 | North Mini Code medium | Cohere | 3.0 | 5.8 | $0.000 | 0/1 | 305.0s |
| #108 | Owl Alpha medium | Openrouter | 3.0 | 5.8 | $0.000 | 0/1 | 2.38s |
| #109 | Mimo V2 PRO none | Xiaomi | 3.0 | 5.8 | $0.045 | 0/1 | 1.63s |
| #110 | Owl Alpha none | Openrouter | 3.0 | 5.8 | $0.000 | 0/1 | 2.50s |
| #111 | Kimi K2.6 none | Moonshot AI | 3.0 | 5.8 | $0.079 | 0/1 | 1.36s |
| #112 | GPT-5.4 none | OpenAI | 3.0 | 5.8 | $0.122 | 0/1 | 990ms |
| #113 | Qwen3.6 Plus Preview medium | Qwen | 3.0 | 5.8 | $0.000 | 0/1 | 0ms |
| #114 | Mimo V2 Omni none | Xiaomi | 3.0 | 5.7 | $0.021 | 0/1 | 1.30s |
| #115 | Grok 4.1 Fast medium | X AI | 3.0 | 5.6 | $0.069 | 0/1 | 25.5s |
| #116 | GLM 5.1 none | Z.ai | 3.0 | 5.6 | $0.058 | 0/1 | 2.34s |
| #117 | DeepSeek V4 Flash none | DeepSeek | 3.0 | 5.5 | $0.007 | 0/1 | 3.07s |
| #118 | Kimi K2.5 none | Moonshot AI | 3.0 | 5.5 | $0.027 | 0/1 | 3.90s |
| #119 | MiMo-V2.5-Pro none | Xiaomi | 3.0 | 5.5 | $0.017 | 0/1 | 1.89s |
| #120 | Qwen3.6 27B none | Qwen | 3.0 | 5.5 | $0.028 | 0/1 | 4.03s |