AI BENCHY 分类
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 ↑.
| 排名 | 模型 | 公司 | 反AI技巧 得分 | 分数 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|
| #96 | Ring-2.6-1T none | Inclusionai | 9.2 | 6.2 | 3/4 | 43.3s |
| #100 | Grok Build 0.1 none | X AI | 8.7 | 6.0 | 3/4 | 6.30s |
| #102 | Gemma 4 26B A4B none | 8.3 | 6.0 | 3/4 | 1.28s | |
| #105 | Nemotron 3 Super medium | NVIDIA | 8.3 | 5.8 | 3/4 | 7.85s |
| #119 | Cobuddy medium | Baidu | 8.7 | 5.6 | 3/4 | 10.00s |
| #1 | Gemini 3 Flash Preview medium | 10.0 | 9.8 | 4/4 | 3.88s | |
| #2 | Gemini 3.5 Flash high | 10.0 | 9.6 | 4/4 | 2.57s | |
| #3 | Gemini 3.5 Flash low | 10.0 | 9.4 | 4/4 | 2.52s | |
| #4 | Gemini 3.1 Pro Preview medium | 10.0 | 9.4 | 4/4 | 7.90s | |
| #5 | Qwen3.7 Max medium | Qwen | 10.0 | 9.1 | 4/4 | 6.36s |
| #6 | GPT-5.5 low | OpenAI | 10.0 | 9.0 | 4/4 | 4.41s |
| #7 | Gemini 3.5 Flash medium | 10.0 | 9.0 | 4/4 | 2.09s | |
| #9 | GPT-5.5 medium | OpenAI | 10.0 | 8.8 | 4/4 | 4.66s |
| #10 | Claude Opus 4.8 medium | Anthropic | 10.0 | 8.7 | 4/4 | 3.95s |
| #12 | Gemini 3.1 Flash Lite Preview high | 10.0 | 8.6 | 3/3 | 43.9s |