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 ↑.
461/461
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） |
|---|---|---|---|---|---|---|---|
| #111 | GPT-5.6 Terra medium | OpenAI | 0.3 | 0.8 | $0.483 | 0/1 | 10.1s |
| #112 | Seed-2.0-Lite medium | Bytedance Seed | 0.3 | 0.8 | $0.271 | 0/1 | 48.3s |
| #113 | Kimi K3.1 Pro high | Moonshot AI | 0.3 | 0.8 | $1.646 | 0/1 | 89.7s |
| #114 | Seed-2.0-Code low | Bytedance Seed | 0.3 | 0.8 | $0.881 | 0/1 | 10.0s |
| #115 | DeepSeek V4 Pro 0423 high | DeepSeek | 0.3 | 0.8 | $0.149 | 0/1 | 34.0s |
| #116 | Claude Opus 4.7 medium | Anthropic | 0.3 | 0.8 | $3.636 | 0/1 | 2.25s |
| #117 | DeepSeek V4 Flash 0423 high | DeepSeek | 0.3 | 0.8 | $0.261 | 0/1 | 54.5s |
| #118 | DeepSeek V4.1 Flash low | DeepSeek | 0.3 | 0.8 | $0.494 | 0/1 | 46.9s |
| #119 | GPT-5.6 Luna high | OpenAI | 0.3 | 0.8 | $0.118 | 0/1 | 17.0s |
| #120 | Nemotron 3 Ultra medium | NVIDIA | 0.3 | 0.8 | $0.674 | 0/1 | 38.5s |
| #121 | GPT-5.4 Nano medium | OpenAI | 0.3 | 0.8 | $0.235 | 0/1 | 4.81s |
| #123 | Qwen3.8 Flash Next low | Qwen | 0.3 | 0.8 | ~$0.045 | 0/1 | 9.26s |
| #124 | GPT-5.6 Terra low | OpenAI | 0.3 | 0.8 | $0.435 | 0/1 | 5.95s |
| #125 | Qwen3.5-27B medium | Qwen | 0.3 | 0.8 | $1.135 | 0/1 | 85.1s |
| #126 | GLM 5.3 FlashX max | Z.ai | 0.3 | 0.8 | $0.623 | 0/1 | 22.4s |