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: 测试正确 ↑.
316/316
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） |
|---|---|---|---|---|---|---|---|
| #129 | Step 3.7 Flash low | Stepfun | 8.7 | 7.1 | $0.390 | 3/4 | 4.02s |
| #130 | Solar Pro 4 high | Upstage | 8.7 | 7.1 | $0.046 | 3/4 | 58.8s |
| #132 | GPT-5.6 Sol none | OpenAI | 8.3 | 7.0 | $0.201 | 3/4 | 1.27s |
| #133 | DeepSeek V3.2 medium | DeepSeek | 8.2 | 7.0 | $0.078 | 3/4 | 24.2s |
| #137 | Grok 4.20 medium | X AI | 8.2 | 7.0 | $0.805 | 3/4 | 3.95s |
| #140 | KAT-Coder-Pro V2.5 medium | Kwaipilot | 8.2 | 6.9 | $0.478 | 3/4 | 3.90s |
| #143 | Seed-2.0-Code high | Bytedance Seed | 8.3 | 6.9 | $1.273 | 3/4 | 35.1s |
| #148 | Solar Pro 4 low | Upstage | 8.2 | 6.8 | $0.044 | 3/4 | 40.2s |
| #149 | Solar Pro 4 medium | Upstage | 8.2 | 6.8 | $0.047 | 3/4 | 53.4s |
| #153 | Gemini 3 Flash Preview none | 8.3 | 6.8 | $0.085 | 3/4 | 1.25s | |
| #155 | GLM 5.2 none | Z.ai | 8.3 | 6.7 | $0.153 | 3/4 | 3.70s |
| #156 | KAT-Coder-Pro V2.5 none | Kwaipilot | 8.7 | 6.7 | $0.487 | 3/4 | 4.58s |
| #160 | LongCat 2.0 high | Meituan | 8.9 | 6.7 | $0.492 | 3/4 | 7.76s |
| #161 | Claude Opus 4.7 none | Anthropic | 8.3 | 6.6 | $0.505 | 3/4 | 2.12s |
| #162 | Gemini 3.5 Flash Lite low | 9.0 | 6.6 | $0.138 | 3/4 | 1.69s |