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 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #267 | Solar Pro 4 high | Upstage | 0.3 | 0.6 | $0.077 | 0/1 | 81.1s |
| #432 | Command A+ high | Cohere | 0.3 | 0.3 | $0.079 | 0/1 | 90.5s |
| #297 | Gemini 3.1 Flash Lite minimal | 0.3 | 0.6 | $0.080 | 0/1 | 724ms | |
| #324 | Nemotron 3 Super medium | NVIDIA | 0.3 | 0.6 | $0.081 | 0/1 | 55.3s |
| #167 | DeepSeek V4 Pro 0423 none | DeepSeek | 0.3 | 0.7 | $0.083 | 0/1 | 5.76s |
| #246 | Laguna XS 2.1 medium | Poolside | 0.3 | 0.6 | $0.083 | 0/1 | 10.9s |
| #420 | Grok 4.20 Beta default | X AI | 0.0 | 0.4 | $0.087 | 0/0 | 0ms |
| #100 | Claude Haiku 5.5 high | Anthropic | 0.3 | 0.8 | $0.088 | 0/1 | 4.49s |
| #58 | GLM 5.3 Flash max | Z.ai | 0.3 | 0.9 | $0.089 | 0/1 | 46.8s |
| #154 | Qwen3.8 27B low | Qwen | 0.3 | 0.8 | ~$0.089 | 0/1 | 12.6s |
| #219 | Qwen3.5-Flash none | Qwen | 0.3 | 0.7 | $0.089 | 0/1 | 588ms |
| #280 | Gemini 3.1 Flash Lite Preview none | 0.3 | 0.6 | $0.090 | 0/1 | 814ms | |
| #358 | Laguna S 2.1 medium | Poolside | 0.3 | 0.5 | $0.092 | 0/1 | 7.11s |
| #250 | Solar Pro 4 medium | Upstage | 0.3 | 0.6 | $0.098 | 0/1 | 108.6s |
| #220 | Solar Pro 4 low | Upstage | 0.3 | 0.7 | $0.101 | 0/1 | 69.2s |