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 ↑.
216/216
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） |
|---|---|---|---|---|---|---|---|
| #114 | Ring-2.6-1T medium | Inclusionai | 7.3 | 6.3 | $0.103 | 1/2 | 257.3s |
| #117 | LongCat 2.0 none | Meituan | 6.5 | 6.3 | $0.044 | 1/2 | 28.4s |
| #118 | Claude Sonnet 5 none | Anthropic | 6.5 | 6.3 | $0.548 | 1/2 | 31.4s |
| #120 | Qwen3.5-Flash medium | Qwen | 6.4 | 6.2 | $0.139 | 1/2 | 266.6s |
| #127 | gpt-oss-120b medium | OpenAI | 6.5 | 6.1 | $0.019 | 1/2 | 24.0s |
| #132 | Qwen3.5 Plus 2026-04-20 none | Qwen | 6.4 | 6.1 | $0.122 | 1/2 | 109.7s |
| #134 | GPT-5 Nano medium | OpenAI | 6.4 | 6.1 | $0.114 | 1/2 | 146.9s |
| #136 | Step 3.5 Flash medium | Stepfun | 6.5 | 6.0 | $0.108 | 1/2 | 813.7s |
| #142 | GPT-5.4 Mini none | OpenAI | 6.5 | 5.9 | $0.095 | 1/2 | 6.22s |
| #146 | Nemotron 3 Super medium | NVIDIA | 6.4 | 5.7 | $0.055 | 1/2 | 259.9s |
| #150 | KAT-Coder-Air V2.5 high | Kwaipilot | 6.5 | 5.6 | $0.077 | 1/2 | 74.5s |
| #155 | KAT-Coder-Air V2.5 medium | Kwaipilot | 6.5 | 5.6 | $0.048 | 1/2 | 19.6s |
| #164 | KAT-Coder-Air V2.5 low | Kwaipilot | 6.4 | 5.4 | $0.041 | 1/2 | 55.9s |
| #168 | Ling-2.6-1T none | Inclusionai | 6.5 | 5.3 | $0.016 | 1/2 | 23.8s |
| #1 | Gemini 3.6 Flash medium | 10.0 | 9.9 | $0.831 | 2/2 | 42.1s |