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: 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 | 通用智能 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #164 | KAT-Coder-Air V2.5 low | Kwaipilot | 5.0 | 5.4 | $0.041 | 0/1 | 10.1s |
| #165 | GPT-5.6 Luna none | OpenAI | 5.0 | 5.4 | $0.142 | 0/1 | 1.00s |
| #166 | Laguna XS 2.1 none | Poolside | 5.0 | 5.3 | $0.008 | 0/1 | 529ms |
| #167 | Qwen3.6 35B A3B none | Qwen | 4.4 | 5.3 | $0.061 | 0/1 | 3.51s |
| #168 | Ling-2.6-1T none | Inclusionai | 5.0 | 5.3 | $0.016 | 0/1 | 20.3s |
| #170 | Inkling none | Thinkingmachines | 5.0 | 5.2 | $0.147 | 0/1 | 859ms |
| #171 | Mistral Small 4 none | Mistral | 4.0 | 5.1 | $0.022 | 0/1 | 729ms |
| #173 | Mistral Small 4 medium | Mistral | 4.8 | 5.1 | $0.096 | 0/1 | 2.05s |
| #174 | MiMo-V2.5 none | Xiaomi | 4.4 | 5.1 | $0.025 | 0/1 | 6.86s |
| #175 | Qwen3.5-9B none | Qwen | 4.4 | 5.1 | $0.021 | 0/1 | 552ms |
| #176 | GLM 5 Turbo none | Z.ai | 4.2 | 5.1 | $0.047 | 0/1 | 2.18s |
| #177 | North Mini Code none | Cohere | 3.9 | 5.1 | $0.000 | 0/1 | 34.8s |
| #178 | MiniMax M2.7 medium | Minimax | 3.9 | 5.0 | $0.163 | 0/1 | 38.7s |
| #179 | DeepSeek V3.2 none | DeepSeek | 4.7 | 5.0 | $0.054 | 0/1 | 9.32s |
| #180 | GPT-4o-mini none | OpenAI | 4.0 | 5.0 | $0.010 | 0/1 | 909ms |