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: 总成本 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #118 | Qwen3.7 Plus none | Qwen | 10.0 | 7.3 | $0.106 | 2/2 | 117.7s |
| #165 | Inkling Small medium | Thinkingmachines | 3.8 | 6.6 | $0.113 | 0/2 | 8.89s |
| #245 | Laguna S 2.1 high | Poolside | 2.9 | 5.4 | $0.114 | 0/2 | 702.3s |
| #138 | Seed-2.0-Mini medium | Bytedance Seed | 7.3 | 7.0 | $0.116 | 1/2 | 282.3s |
| #105 | Gemini 3.1 Flash Lite Preview medium | 7.2 | 7.4 | $0.117 | 1/2 | 16.6s | |
| #204 | GPT-5 Nano medium | OpenAI | 6.4 | 6.0 | $0.118 | 1/2 | 146.9s |
| #117 | Gemini 3.1 Flash Lite medium | 7.2 | 7.3 | $0.120 | 1/2 | 18.5s | |
| #197 | Qwen3.5 Plus 2026-04-20 none | Qwen | 6.4 | 6.1 | $0.122 | 1/2 | 109.7s |
| #207 | Step 3.5 Flash medium | Stepfun | 6.5 | 5.9 | $0.132 | 1/2 | 813.7s |
| #232 | Nemotron 3.5 Lightning high | NVIDIA | 6.4 | 5.6 | $0.134 | 1/2 | 160.5s |
| #210 | Hy3 preview high | Tencent | 5.0 | 5.9 | $0.135 | 1/1 | 113.1s |
| #162 | Gemini 3.5 Flash Lite low | 3.8 | 6.6 | $0.138 | 0/2 | 11.0s | |
| #275 | Nemotron 3.5 Lightning low | NVIDIA | 6.3 | 4.8 | $0.140 | 1/2 | 142.4s |
| #192 | Qwen3.5-Flash medium | Qwen | 6.4 | 6.1 | $0.142 | 1/2 | 266.6s |
| #95 | GPT-5.4 Nano medium | OpenAI | 9.9 | 7.5 | $0.142 | 2/2 | 32.2s |