通用智能 排名
看看哪些 AI 模型在 通用智能 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: 指标 ↑.
319/319
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 | 通用智能 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #128 | Qwen3.7 Flash low | Qwen | 4.0 | 7.2 | $0.043 | 0/1 | 14.4s |
| #76 | Step 3.7 Flash medium | Stepfun | 4.0 | 7.9 | $0.495 | 0/1 | 6.85s |
| #167 | Gemini 3.1 Flash Lite Preview low | 4.0 | 6.6 | $0.646 | 0/1 | 1.54s | |
| #169 | Gemini 3.1 Flash Lite low | 4.0 | 6.6 | $0.621 | 0/1 | 1.37s | |
| #176 | Gemini 3.1 Flash Lite Preview none | 4.0 | 6.4 | $0.052 | 0/1 | 741ms | |
| #185 | MiMo-V2-Flash medium | Xiaomi | 4.0 | 6.3 | $0.043 | 0/1 | 4.20s |
| #190 | Gemini 3.1 Flash Lite minimal | 4.0 | 6.1 | $0.047 | 0/1 | 791ms | |
| #194 | Gemini 3.1 Flash Lite none | 4.0 | 6.1 | $0.046 | 0/1 | 992ms | |
| #231 | Gemma 4 26B A4B none | 4.0 | 5.6 | $0.015 | 0/1 | 3.54s | |
| #245 | MiMo-V2.5-Pro none | Xiaomi | 4.0 | 5.4 | $0.068 | 0/1 | 2.58s |
| #257 | Granite 4.2 8B medium | IBM Granite | 4.0 | 5.2 | $0.009 | 0/1 | 605ms |
| #259 | Mistral Small 4 none | Mistral | 4.0 | 5.1 | $0.022 | 0/1 | 729ms |
| #261 | Granite 4.2 8B low | IBM Granite | 4.0 | 5.1 | $0.012 | 0/1 | 659ms |
| #271 | GPT-4o-mini none | OpenAI | 4.0 | 5.0 | $0.010 | 0/1 | 909ms |
| #274 | Ling-2.6-flash none | Inclusionai | 4.0 | 4.9 | $0.002 | 0/1 | 1.45s |