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 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #221 | Grok 4.7 high | X AI | 0.9 | 0.7 | $3.037 | 3/4 | 28.0s |
| #223 | Ember-1 max | Fireworks | 0.9 | 0.7 | $3.264 | 3/4 | 23.7s |
| #225 | GPT-5.6 Sol none | OpenAI | 0.8 | 0.7 | $0.795 | 3/4 | 1.27s |
| #227 | GLM 5.3 Flash low | Z.ai | 0.9 | 0.7 | $0.038 | 3/4 | 2.14s |
| #229 | GLM 5.2 none | Z.ai | 0.8 | 0.7 | $0.250 | 3/4 | 3.70s |
| #241 | Beam 1.0 501B A23B xhigh | Reflection | 0.9 | 0.6 | $0.688 | 3/4 | 1.52s |
| #248 | Gemini 3 Flash Preview none | 0.8 | 0.6 | $0.155 | 3/4 | 1.25s | |
| #250 | Solar Pro 4 medium | Upstage | 0.8 | 0.6 | $0.098 | 3/4 | 53.4s |
| #258 | Dots 3 Note Preview high | Dots Studio | 0.9 | 0.6 | $0.000 | 3/4 | 6.97s |
| #263 | Gemini 3.5 Flash Lite low | 0.9 | 0.6 | $0.183 | 3/4 | 1.69s | |
| #264 | Gemini 3.1 Flash Lite Preview low | 0.8 | 0.6 | $0.736 | 3/4 | 2.12s | |
| #267 | Solar Pro 4 high | Upstage | 0.9 | 0.6 | $0.077 | 3/4 | 58.8s |
| #272 | DeepSeek V3.2 medium | DeepSeek | 0.8 | 0.6 | $0.152 | 3/4 | 24.2s |
| #273 | Trinity Large Thinking low | Arcee AI | 0.8 | 0.6 | $0.918 | 3/4 | 5.70s |
| #275 | Grok 4.20 medium | X AI | 0.8 | 0.6 | $1.246 | 3/4 | 3.95s |