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） |
|---|---|---|---|---|---|---|---|
| #33 | Qwen3.5 Plus 2026-04-20 medium | Qwen | 3.0 | 7.8 | $0.317 | 0/1 | 92.6s |
| #21 | GLM 5 Turbo medium | Z.ai | 3.0 | 8.4 | $0.323 | 0/1 | 40.2s |
| #14 | GLM 5.2 medium | Z.ai | 3.0 | 8.7 | $0.324 | 0/1 | 34.2s |
| #77 | Mimo V2 PRO medium | Xiaomi | 3.0 | 6.7 | $0.333 | 0/1 | 82.7s |
| #39 | Step 3.7 Flash low | Stepfun | 3.0 | 7.7 | $0.341 | 0/1 | 124.8s |
| #43 | Kimi K2.5 medium | Moonshot AI | 3.0 | 7.5 | $0.348 | 0/1 | 83.9s |
| #5 | Gemini 3.5 Flash low | 10.0 | 9.2 | $0.349 | 1/1 | 1.88s | |
| #20 | Step 3.7 Flash medium | Stepfun | 3.0 | 8.5 | $0.376 | 0/1 | 114.0s |
| #24 | Gemini 2.5 Flash medium | 3.0 | 8.2 | $0.379 | 0/1 | 2.76s | |
| #91 | Gemini 3 PRO Preview medium | 3.0 | 6.2 | $0.385 | 0/1 | 0ms | |
| #19 | GPT-5.2 Chat none | OpenAI | 3.0 | 8.5 | $0.393 | 0/1 | 6.89s |
| #89 | Qwen3.5-35B-A3B medium | Qwen | 3.0 | 6.3 | $0.401 | 0/1 | 177.4s |
| #45 | GPT-5.3 Chat none | OpenAI | 3.0 | 7.5 | $0.433 | 0/1 | 4.38s |
| #81 | Qwen3.6 27B medium | Qwen | 3.0 | 6.6 | $0.440 | 0/1 | 81.0s |
| #56 | GLM 5V Turbo medium | Z.ai | 3.0 | 7.3 | $0.457 | 0/1 | 41.0s |