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 ↓.
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） |
|---|---|---|---|---|---|---|---|
| #72 | Muse Spark 1.1 low | Meta | 3.0 | 8.3 | $0.673 | 0/1 | 8.17s |
| #130 | Kimi K2.7 Code medium | Moonshot AI | 3.0 | 7.4 | $0.671 | 0/1 | 341.8s |
| #32 | Gemini 3.5 Flash medium | 10.0 | 9.0 | $0.665 | 1/1 | 2.75s | |
| #27 | Qwen3.8 Max (0902) low | Qwen | 3.0 | 9.1 | $0.664 | 0/1 | 13.3s |
| #137 | Claude Sonnet 4.6 none | Anthropic | 3.0 | 7.3 | $0.661 | 0/1 | 4.67s |
| #61 | Muse Spark 1.2 low | Meta | 3.0 | 8.4 | $0.655 | 0/1 | 10.00s |
| #26 | Gemini 3.8 Flash medium | 10.0 | 9.1 | $0.653 | 1/1 | 5.94s | |
| #195 | Gemini 3.1 Flash Lite Preview low | 3.0 | 6.6 | $0.646 | 0/1 | 1.35s | |
| #7 | Gemini 3.7 Flash high | 10.0 | 9.8 | $0.646 | 1/1 | 5.60s | |
| #75 | Gemini 2.5 Flash medium | 3.0 | 8.2 | $0.644 | 0/1 | 2.76s | |
| #235 | Trinity Large Thinking low | Arcee AI | 3.0 | 6.0 | $0.625 | 0/1 | 2.10s |
| #197 | Gemini 3.1 Flash Lite low | 3.0 | 6.6 | $0.621 | 0/1 | 1.46s | |
| #91 | GPT-5.2 Chat none | OpenAI | 3.0 | 7.9 | $0.594 | 0/1 | 6.89s |
| #318 | Trinity Large Thinking high | Arcee AI | 3.0 | 4.8 | $0.592 | 0/1 | 125.1s |
| #114 | Nemotron 3 Ultra medium | NVIDIA | 3.0 | 7.6 | $0.567 | 0/1 | 38.5s |