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） |
|---|---|---|---|---|---|---|---|
| #270 | Claude Opus 4.6 medium | Anthropic | 0.6 | 0.6 | $2.961 | 2/4 | 7.45s |
| #276 | Space Bunny Alpha xhigh | Stealth | 0.6 | 0.6 | $0.000 | 2/4 | 3.02s |
| #280 | Gemini 3.1 Flash Lite Preview none | 0.7 | 0.6 | $0.090 | 2/4 | 1.04s | |
| #281 | Claude Fable 5.1 low | Anthropic | 0.7 | 0.6 | $3.395 | 2/4 | 4.54s |
| #284 | Trinity Large Thinking medium | Arcee AI | 0.7 | 0.6 | $0.862 | 2/4 | 5.11s |
| #288 | Step 5 Preview medium | Stepfun | 0.6 | 0.6 | $4.136 | 2/4 | 12.6s |
| #298 | gpt-oss-120b medium | OpenAI | 0.7 | 0.6 | $0.030 | 2/4 | 10.2s |
| #299 | Gemini 3.1 Flash Lite none | 0.8 | 0.6 | $0.069 | 2/4 | 1.07s | |
| #304 | Qwen3.8 Flash Next none | Qwen | 0.7 | 0.6 | ~$0.011 | 2/4 | 1.70s |
| #310 | Trinity Large Thinking high | Arcee AI | 0.7 | 0.6 | $0.794 | 2/4 | 4.13s |
| #311 | GPT-5 Nano medium | OpenAI | 0.6 | 0.6 | $0.159 | 2/4 | 25.5s |
| #316 | Gemma 4 31B none | 0.7 | 0.6 | $0.031 | 2/4 | 1.85s | |
| #317 | Space Bunny Alpha low | Stealth | 0.7 | 0.6 | $0.000 | 2/4 | 2.75s |
| #320 | Step 5 Preview low | Stepfun | 0.7 | 0.6 | $4.110 | 2/4 | 9.50s |
| #323 | Nemotron 3.5 Super VL none | NVIDIA | 0.7 | 0.6 | $0.040 | 2/4 | 3.08s |