反AI技巧 排名
看看哪些 AI 模型在 反AI技巧 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 ↓.
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 | 反AI技巧 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #174 | LongCat 2.0 high | Meituan | 0.9 | 0.7 | $0.778 | 3/4 | 7.76s |
| #122 | Gemini 3.8 Flash medium | 1.0 | 0.8 | $0.769 | 4/4 | 2.66s | |
| #183 | LongCat 2.0 medium | Meituan | 1.0 | 0.7 | $0.767 | 4/4 | 9.65s |
| #108 | DeepSeek V4.1 Flash 1017 max | DeepSeek | 0.8 | 0.8 | $0.757 | 3/4 | 4.16s |
| #12 | GPT-6.1 Sol high | OpenAI | 1.0 | 1.0 | $0.755 | 4/4 | 3.31s |
| #51 | Gemini 3.5 Flash low | 1.0 | 0.9 | $0.752 | 4/4 | 2.52s | |
| #364 | Grok 4.20 Beta medium | X AI | 0.9 | 0.5 | $0.750 | 3/4 | 3.16s |
| #290 | KAT-Coder-Pro V2.5 default | Kwaipilot | 0.9 | 0.6 | $0.742 | 3/4 | 4.58s |
| #264 | Gemini 3.1 Flash Lite Preview low | 0.8 | 0.6 | $0.736 | 3/4 | 2.12s | |
| #266 | Gemini 3.1 Flash Lite low | 0.7 | 0.6 | $0.717 | 2/4 | 1.84s | |
| #261 | Qwen3.5-35B-A3B medium | Qwen | 1.0 | 0.6 | $0.716 | 4/4 | 21.1s |
| #20 | GPT-6 Sol medium | OpenAI | 1.0 | 0.9 | $0.703 | 4/4 | 2.70s |
| #99 | GPT-5.6 Terra high | OpenAI | 0.8 | 0.8 | $0.698 | 3/4 | 2.54s |
| #318 | GPT-5.4 none | OpenAI | 0.3 | 0.6 | $0.690 | 0/4 | 1.21s |
| #241 | Beam 1.0 501B A23B xhigh | Reflection | 0.9 | 0.6 | $0.688 | 3/4 | 1.52s |