综合 排名
看看哪些 AI 模型在 综合 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 | 综合 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #137 | Grok 4.20 medium | X AI | 8.7 | 7.0 | $0.805 | 1/2 | 42.2s |
| #138 | Seed-2.0-Mini medium | Bytedance Seed | 7.3 | 7.0 | $0.116 | 1/2 | 282.3s |
| #139 | Kimi K2.5 medium | Moonshot AI | 6.7 | 7.0 | $0.479 | 1/2 | 89.2s |
| #140 | KAT-Coder-Pro V2.5 medium | Kwaipilot | 6.4 | 6.9 | $0.478 | 1/2 | 135.7s |
| #142 | Qwen3.7 Flash medium | Qwen | 6.4 | 6.9 | $0.065 | 1/2 | 314.2s |
| #143 | Seed-2.0-Code high | Bytedance Seed | 7.3 | 6.9 | $1.273 | 1/2 | 144.9s |
| #145 | Qwen3.6 Flash medium | Qwen | 6.5 | 6.8 | $0.741 | 1/2 | 299.2s |
| #146 | Step 3.7 Flash high | Stepfun | 8.7 | 6.8 | $1.229 | 1/2 | 41.2s |
| #148 | Solar Pro 4 low | Upstage | 6.3 | 6.8 | $0.044 | 1/2 | 358.1s |
| #149 | Solar Pro 4 medium | Upstage | 6.4 | 6.8 | $0.047 | 1/2 | 294.8s |
| #150 | DeepSeek V4 Pro none | DeepSeek | 7.9 | 6.8 | $0.220 | 1/2 | 71.6s |
| #152 | MiMo-V2.5-Pro medium | Xiaomi | 6.9 | 6.8 | $0.221 | 1/2 | 125.4s |
| #154 | Gemma 4 26B A4B medium | 6.3 | 6.8 | $0.092 | 1/2 | 492.9s | |
| #155 | GLM 5.2 none | Z.ai | 6.9 | 6.7 | $0.153 | 1/2 | 50.2s |
| #163 | Qwen3.5-27B none | Qwen | 6.4 | 6.6 | $0.058 | 1/2 | 39.4s |