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 ↑.
461/461
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） |
|---|---|---|---|---|---|---|---|
| #276 | Space Bunny Alpha xhigh | Stealth | 0.5 | 0.6 | $0.000 | 0/1 | 4.74s |
| #277 | KAT-Coder-Pro V2.5 medium | Kwaipilot | 0.5 | 0.6 | $0.669 | 0/1 | 2.35s |
| #278 | GLM 5 Turbo medium | Z.ai | 0.6 | 0.6 | $0.323 | 0/1 | 10.1s |
| #279 | DeepSeek V4 Flash 0731 none | DeepSeek | 0.4 | 0.6 | $0.053 | 0/1 | 3.22s |
| #280 | Gemini 3.1 Flash Lite Preview none | 0.4 | 0.6 | $0.090 | 0/1 | 741ms | |
| #283 | Beam 1.0 501B A23B high | Reflection | 0.5 | 0.6 | $0.674 | 0/1 | 1.94s |
| #285 | Apodex 1.1 Mini low | Apodex | 0.5 | 0.6 | $0.000 | 0/1 | 18.0s |
| #286 | Inkling none | Thinkingmachines | 0.5 | 0.6 | $0.292 | 0/1 | 859ms |
| #287 | Qwen3.5 Plus 2026-04-20 none | Qwen | 0.5 | 0.6 | $0.216 | 0/1 | 1.41s |
| #288 | Step 5 Preview medium | Stepfun | 0.3 | 0.6 | $4.136 | 0/1 | 34.8s |
| #289 | Granite 4.2 8B medium | IBM Granite | 0.4 | 0.6 | $0.029 | 0/1 | 605ms |
| #290 | KAT-Coder-Pro V2.5 default | Kwaipilot | 0.5 | 0.6 | $0.742 | 0/1 | 5.16s |
| #291 | Apodex 1.1 Mini medium | Apodex | 0.5 | 0.6 | $0.000 | 0/1 | 16.1s |
| #292 | Claude Sonnet 4.6 none | Anthropic | 0.6 | 0.6 | $0.661 | 0/1 | 2.56s |
| #293 | GLM 5.3 FlashX low | Z.ai | 0.5 | 0.6 | $0.157 | 0/1 | 2.07s |