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） |
|---|---|---|---|---|---|---|---|
| #92 | Solar Pro 4 xhigh | Upstage | 8.3 | 7.6 | $0.050 | 3/4 | 64.2s |
| #95 | GPT-5.4 Nano medium | OpenAI | 8.3 | 7.5 | $0.142 | 3/4 | 4.52s |
| #96 | GPT-5.6 Terra low | OpenAI | 8.3 | 7.5 | $0.420 | 3/4 | 2.36s |
| #99 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 8.2 | 7.5 | $0.459 | 3/4 | 45.8s |
| #100 | Qwen3.5-27B medium | Qwen | 8.7 | 7.5 | $0.982 | 3/4 | 19.8s |
| #102 | GPT-5.4 Mini medium | OpenAI | 8.6 | 7.5 | $0.786 | 3/4 | 4.05s |
| #103 | Grok Build 0.1 medium | X AI | 8.3 | 7.5 | $1.130 | 3/4 | 7.43s |
| #105 | Gemini 3.1 Flash Lite Preview medium | 9.1 | 7.4 | $0.117 | 3/4 | 2.33s | |
| #108 | GPT-5.6 Luna medium | OpenAI | 8.3 | 7.4 | $0.072 | 3/4 | 2.52s |
| #116 | GLM 5.3 Flash high | Z.ai | 8.3 | 7.3 | $0.029 | 3/4 | 2.50s |
| #117 | Gemini 3.1 Flash Lite medium | 9.1 | 7.3 | $0.120 | 3/4 | 2.39s | |
| #119 | DeepSeek V4 Flash 0731 medium | DeepSeek | 8.2 | 7.3 | $0.066 | 3/4 | 18.0s |
| #123 | Muse Glimmer 30B high | Meta | 8.7 | 7.2 | $0.397 | 3/4 | 13.2s |
| #126 | Muse Glimmer 30B medium | Meta | 9.2 | 7.2 | $0.211 | 3/4 | 7.36s |
| #128 | Muse Glimmer 30B low | Meta | 8.7 | 7.1 | $0.143 | 3/4 | 3.57s |