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） |
|---|---|---|---|---|---|---|---|
| #239 | Mercury 2.5 Preview high | Inception | 0.3 | 0.6 | $0.040 | 0/1 | 5.41s |
| #323 | Nemotron 3.5 Super VL none | NVIDIA | 0.3 | 0.6 | $0.040 | 0/1 | 10.6s |
| #371 | Qwen3.5-9B none | Qwen | 0.3 | 0.5 | $0.041 | 0/1 | 2.32s |
| #340 | GPT-5.6 Luna none | OpenAI | 0.3 | 0.5 | $0.042 | 0/1 | 651ms |
| #392 | Hy3 preview low | Tencent | 0.3 | 0.5 | $0.042 | 0/1 | 41.7s |
| #351 | MiMo-V2-Flash medium | Xiaomi | 0.3 | 0.5 | $0.043 | 0/1 | 1.96s |
| #240 | Mercury 2.5 high | Inception | 0.3 | 0.6 | $0.044 | 0/1 | 5.48s |
| #379 | Laguna S 2.1 none | Poolside | 0.3 | 0.5 | $0.044 | 0/1 | 200.5s |
| #123 | Qwen3.8 Flash Next low | Qwen | 0.3 | 0.8 | ~$0.045 | 0/1 | 9.26s |
| #389 | Mimo V2 PRO default | Xiaomi | 0.3 | 0.5 | $0.045 | 0/1 | 1.63s |
| #363 | KAT Coder AIR V2.5 low | Kwaipilot | 0.3 | 0.5 | $0.046 | 0/1 | 20.0s |
| #405 | GLM 5 Turbo none | Z.ai | 0.3 | 0.4 | $0.047 | 0/1 | 2.37s |
| #353 | Mistral Small 4 none | Mistral | 0.3 | 0.5 | $0.047 | 0/1 | 397ms |
| #103 | GPT-6 Luna medium | OpenAI | 0.3 | 0.8 | $0.047 | 0/1 | 6.39s |
| #152 | Qwen3.8 Flash Next medium | Qwen | 0.3 | 0.8 | ~$0.047 | 0/1 | 24.4s |