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） |
|---|---|---|---|---|---|---|---|
| #76 | MiMo-V2.5 medium | Xiaomi | 3.0 | 6.7 | $0.063 | 0/1 | 51.3s |
| #77 | Mimo V2 PRO medium | Xiaomi | 3.0 | 6.7 | $0.333 | 0/1 | 82.7s |
| #78 | gpt-oss-120b medium | OpenAI | 3.0 | 6.7 | $0.013 | 0/1 | 26.5s |
| #79 | GPT-5 Nano medium | OpenAI | 3.0 | 6.7 | $0.081 | 0/1 | 20.1s |
| #80 | Step 3.5 Flash medium | Stepfun | 3.0 | 6.6 | $0.070 | 0/1 | 108.4s |
| #81 | Qwen3.6 27B medium | Qwen | 3.0 | 6.6 | $0.440 | 0/1 | 81.0s |
| #82 | Gemini 3.1 Flash Lite Preview low | 3.0 | 6.5 | $0.026 | 0/1 | 1.35s | |
| #83 | Gemini 3.1 Flash Lite high | 0.0 | 6.5 | $2.044 | 0/0 | 0ms | |
| #84 | Gemini 3.1 Flash Lite Preview none | 3.0 | 6.4 | $0.018 | 0/1 | 814ms | |
| #85 | Gemini 3.1 Flash Lite low | 3.0 | 6.4 | $0.028 | 0/1 | 1.46s | |
| #86 | Hy3 preview low | Tencent | 3.0 | 6.4 | $0.018 | 0/1 | 41.7s |
| #87 | Nemotron 3 Super medium | NVIDIA | 3.0 | 6.3 | $0.021 | 0/1 | 55.3s |
| #88 | Gemma 4 31B medium | 3.0 | 6.3 | $0.033 | 0/1 | 90.1s | |
| #89 | Qwen3.5-35B-A3B medium | Qwen | 3.0 | 6.3 | $0.401 | 0/1 | 177.4s |
| #90 | GPT-5.5 none | OpenAI | 3.0 | 6.3 | $0.231 | 0/1 | 5.01s |