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） |
|---|---|---|---|---|---|---|---|
| #26 | Nemotron 3 Ultra 550b A55b medium | NVIDIA | 3.0 | 8.1 | $0.158 | 0/1 | 38.5s |
| #41 | DeepSeek V4 Pro high | DeepSeek | 3.0 | 7.6 | $0.157 | 0/1 | 34.0s |
| #75 | Qwen3.6 35B A3B medium | Qwen | 3.0 | 6.7 | $0.146 | 0/1 | 32.9s |
| #40 | MiniMax M3 medium | Minimax | 3.0 | 7.6 | $0.131 | 0/1 | 100.8s |
| #112 | GPT-5.4 none | OpenAI | 3.0 | 5.8 | $0.122 | 0/1 | 990ms |
| #52 | Gemini 3 Flash Preview low | 10.0 | 7.4 | $0.111 | 1/1 | 2.75s | |
| #71 | Gemini 3.5 Flash minimal | 3.0 | 6.8 | $0.108 | 0/1 | 1.76s | |
| #46 | GPT-5.4 Nano medium | OpenAI | 3.0 | 7.5 | $0.107 | 0/1 | 4.81s |
| #51 | MiMo-V2.5-Pro medium | Xiaomi | 3.0 | 7.4 | $0.106 | 0/1 | 12.5s |
| #127 | MiniMax M2.7 medium | Minimax | 3.0 | 5.2 | $0.104 | 0/1 | 22.8s |
| #149 | Grok 4.20 Beta none | X AI | 0.0 | 4.7 | $0.087 | 0/0 | 0ms |
| #79 | GPT-5 Nano medium | OpenAI | 3.0 | 6.7 | $0.081 | 0/1 | 20.1s |
| #70 | Qwen3.5-Flash medium | Qwen | 3.0 | 6.8 | $0.080 | 0/1 | 49.0s |
| #111 | Kimi K2.6 none | Moonshot AI | 3.0 | 5.8 | $0.079 | 0/1 | 1.36s |
| #61 | GLM 5.2 none | Z.ai | 3.0 | 7.1 | $0.076 | 0/1 | 3.41s |