通用智能 排名
看看哪些 AI 模型在 通用智能 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 ↑.
319/319
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 | 通用智能 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #185 | MiMo-V2-Flash medium | Xiaomi | 4.0 | 6.3 | $0.043 | 0/1 | 4.20s |
| #151 | Solar Pro 4 low | Upstage | 5.5 | 6.8 | $0.044 | 0/1 | 61.2s |
| #180 | LongCat 2.0 none | Meituan | 5.0 | 6.4 | $0.044 | 0/1 | 2.76s |
| #232 | Mimo V2 PRO none | Xiaomi | 4.3 | 5.6 | $0.045 | 0/1 | 2.44s |
| #243 | KAT-Coder-Air V2.5 low | Kwaipilot | 5.0 | 5.4 | $0.046 | 0/1 | 10.1s |
| #194 | Gemini 3.1 Flash Lite none | 4.0 | 6.1 | $0.046 | 0/1 | 992ms | |
| #133 | Solar Pro 4 high | Upstage | 5.5 | 7.1 | $0.046 | 0/1 | 42.2s |
| #265 | GLM 5 Turbo none | Z.ai | 4.2 | 5.1 | $0.047 | 0/1 | 2.18s |
| #190 | Gemini 3.1 Flash Lite minimal | 4.0 | 6.1 | $0.047 | 0/1 | 791ms | |
| #152 | Solar Pro 4 medium | Upstage | 3.0 | 6.8 | $0.047 | 0/1 | 48.0s |
| #234 | KAT-Coder-Air V2.5 medium | Kwaipilot | 5.0 | 5.6 | $0.048 | 0/1 | 9.81s |
| #175 | Hy3 preview medium | Tencent | 10.0 | 6.5 | $0.049 | 1/1 | 16.8s |
| #220 | Nemotron 3 Super medium | NVIDIA | 4.1 | 5.7 | $0.050 | 0/1 | 6.91s |
| #95 | Solar Pro 4 xhigh | Upstage | 5.5 | 7.6 | $0.050 | 0/1 | 61.9s |
| #254 | Qwen3.6 35B A3B none | Qwen | 4.4 | 5.3 | $0.051 | 0/1 | 3.51s |