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: 响应时间（平均） ↓.
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） |
|---|---|---|---|---|---|---|---|
| #80 | Muse Glimmer 30B xhigh | Meta | 3.0 | 8.1 | $0.510 | 0/1 | 87.2s |
| #43 | Muse Spark 1.3 medium | Meta | 3.0 | 8.8 | $1.469 | 0/1 | 85.6s |
| #123 | Qwen3.5-27B medium | Qwen | 3.0 | 7.5 | $0.982 | 0/1 | 85.1s |
| #172 | Space Bunny Alpha max | Stealth | 3.0 | 6.9 | $0.000 | 0/1 | 84.9s |
| #160 | DeepSeek V3.2 medium | DeepSeek | 3.0 | 7.0 | $0.078 | 0/1 | 84.0s |
| #167 | Kimi K2.5 medium | Moonshot AI | 3.0 | 7.0 | $0.479 | 0/1 | 83.9s |
| #215 | Mimo V2 PRO medium | Xiaomi | 3.0 | 6.3 | $0.333 | 0/1 | 82.7s |
| #155 | Solar Pro 4 high | Upstage | 3.0 | 7.1 | $0.138 | 0/1 | 81.1s |
| #201 | Qwen3.6 27B medium | Qwen | 3.0 | 6.5 | $0.770 | 0/1 | 81.0s |
| #330 | MiniMax M2.5 medium | Minimax | 3.0 | 4.6 | $0.327 | 0/1 | 80.8s |
| #40 | Seed 2.1 Turbo high | Bytedance Seed | 3.0 | 8.9 | $1.797 | 0/1 | 78.6s |
| #270 | Nemotron 3.5 Lightning high | NVIDIA | 3.0 | 5.6 | $0.134 | 0/1 | 78.0s |
| #89 | Grok 4.7 low | X AI | 3.0 | 7.9 | $1.320 | 0/1 | 76.8s |
| #361 | Command A+ none | Cohere | 3.0 | 3.0 | $0.000 | 0/1 | 74.5s |
| #60 | Grok 4.5 medium | X AI | 3.0 | 8.5 | $2.042 | 0/1 | 74.4s |