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。
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） |
|---|---|---|---|---|---|---|---|
| #172 | Hy3 preview medium | Tencent | 5.0 | 6.5 | $0.049 | 1/1 | 46.0s |
| #201 | Grok 4.20 Beta medium | X AI | 5.0 | 6.0 | $0.750 | 1/1 | 20.9s |
| #209 | Mimo V2 Omni medium | Xiaomi | 5.0 | 5.9 | $0.683 | 1/1 | 25.9s |
| #210 | Hy3 preview high | Tencent | 5.0 | 5.9 | $0.135 | 1/1 | 113.1s |
| #224 | Gemini 3.1 Flash Lite high | 5.0 | 5.6 | $2.044 | 1/1 | 149.2s | |
| #235 | Hy3 preview low | Tencent | 5.0 | 5.5 | $0.042 | 1/1 | 78.7s |
| #250 | Gemini 3.1 Flash Lite Preview high | 5.0 | 5.3 | $2.310 | 1/1 | 280.5s | |
| #269 | Qwen3.6 Plus Preview medium | Qwen | 5.0 | 4.9 | $0.000 | 1/1 | 35.0s |
| #283 | Grok 4.1 Fast medium | X AI | 5.0 | 4.7 | $0.069 | 1/1 | 37.6s |
| #182 | MiMo-V2-Flash medium | Xiaomi | 4.9 | 6.3 | $0.043 | 1/1 | 75.7s |
| #161 | Claude Opus 4.7 none | Anthropic | 4.8 | 6.6 | $0.505 | 1/1 | 18.3s |
| #267 | DeepSeek V3.2 none | DeepSeek | 4.8 | 5.0 | $0.054 | 0/2 | 113.5s |
| #147 | Seed-2.0-Code medium | Bytedance Seed | 4.7 | 6.8 | $1.153 | 0/2 | 102.3s |
| #238 | DeepSeek V4 Flash 0423 none | DeepSeek | 4.6 | 5.4 | $0.039 | 0/2 | 179.6s |
| #156 | KAT-Coder-Pro V2.5 none | Kwaipilot | 4.1 | 6.7 | $0.487 | 0/2 | 183.1s |