领域专项 排名
看看哪些 AI 模型在 领域专项 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 ↓.
316/316
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 | 领域专项 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #138 | Seed-2.0-Mini medium | Bytedance Seed | 3.0 | 7.0 | $0.116 | 0/3 | 103.4s |
| #139 | Kimi K2.5 medium | Moonshot AI | 2.9 | 7.0 | $0.479 | 0/3 | 111.6s |
| #140 | KAT-Coder-Pro V2.5 medium | Kwaipilot | 2.9 | 6.9 | $0.478 | 0/3 | 35.1s |
| #141 | Claude Fable 5.1 low | Anthropic | 4.1 | 6.9 | $2.565 | 0/3 | 19.3s |
| #142 | Qwen3.7 Flash medium | Qwen | 2.9 | 6.9 | $0.065 | 0/3 | 38.0s |
| #143 | Seed-2.0-Code high | Bytedance Seed | 3.5 | 6.9 | $1.273 | 0/3 | 419.7s |
| #145 | Qwen3.6 Flash medium | Qwen | 2.9 | 6.8 | $0.741 | 0/3 | 17.0s |
| #146 | Step 3.7 Flash high | Stepfun | 3.6 | 6.8 | $1.229 | 0/3 | 189.3s |
| #148 | Solar Pro 4 low | Upstage | 2.9 | 6.8 | $0.044 | 0/3 | 279.0s |
| #149 | Solar Pro 4 medium | Upstage | 3.0 | 6.8 | $0.047 | 0/3 | 201.8s |
| #150 | DeepSeek V4 Pro none | DeepSeek | 3.0 | 6.8 | $0.220 | 0/3 | 4.91s |
| #152 | MiMo-V2.5-Pro medium | Xiaomi | 2.9 | 6.8 | $0.221 | 0/3 | 146.1s |
| #156 | KAT-Coder-Pro V2.5 none | Kwaipilot | 4.1 | 6.7 | $0.487 | 0/3 | 24.9s |
| #157 | LongCat 2.0 low | Meituan | 2.9 | 6.7 | $0.412 | 0/3 | 183.6s |
| #160 | LongCat 2.0 high | Meituan | 3.6 | 6.7 | $0.492 | 0/3 | 433.7s |