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: 指标 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #132 | LongCat 2.0 medium | Meituan | 3.0 | 7.4 | $0.499 | 0/1 | 191.2s |
| #133 | Qwen3.8 2.4T A95B high | Qwen | 3.0 | 7.4 | $2.357 | 0/1 | 348.0s |
| #134 | MiMo-V2.6-Flash medium | Xiaomi | 3.0 | 7.4 | $0.190 | 0/1 | 357.3s |
| #135 | Grok 4.6 low | X AI | 3.0 | 7.4 | $0.449 | 0/1 | 26.1s |
| #137 | Claude Sonnet 4.6 none | Anthropic | 3.0 | 7.3 | $0.661 | 0/1 | 4.67s |
| #138 | GLM 5.3 high | Z.ai | 3.0 | 7.3 | $0.242 | 0/1 | 22.0s |
| #139 | KAT-Coder-Pro V2.5 low | Kwaipilot | 3.0 | 7.3 | $0.400 | 0/1 | 17.1s |
| #140 | GLM 5.3 Flash high | Z.ai | 3.0 | 7.3 | $0.057 | 0/1 | 11.5s |
| #141 | Gemini 3.1 Flash Lite medium | 3.0 | 7.3 | $0.120 | 0/1 | 3.08s | |
| #142 | Qwen3.7 Plus none | Qwen | 3.0 | 7.3 | $0.106 | 0/1 | 1.21s |
| #143 | DeepSeek V4 Flash 0731 medium | DeepSeek | 3.0 | 7.3 | $0.216 | 0/1 | 56.6s |
| #144 | Claude Opus 4.8 none | Anthropic | 3.0 | 7.3 | $1.166 | 0/1 | 3.41s |
| #145 | Kimi K2.6 medium | Moonshot AI | 3.0 | 7.2 | $1.247 | 0/1 | 130.3s |
| #146 | KAT-Coder-Pro V2.5 high | Kwaipilot | 3.0 | 7.2 | $0.506 | 0/1 | 5.22s |
| #147 | Muse Glimmer 30B high | Meta | 3.0 | 7.2 | $0.430 | 0/1 | 94.2s |