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: 总成本 ↓.
311/311
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） |
|---|---|---|---|---|---|---|---|
| #273 | Grok 4.20 Multi Agent Beta medium | X AI | 6.9 | 4.8 | $5.599 | 2/4 | 3.46s |
| #22 | GPT-5.5 medium | OpenAI | 10.0 | 9.0 | $4.163 | 4/4 | 4.66s |
| #66 | Kimi K3 max | Moonshot AI | 10.0 | 7.9 | $3.467 | 4/4 | 10.2s |
| #20 | Claude Fable 5.1 high | Anthropic | 10.0 | 9.0 | $3.364 | 4/4 | 5.90s |
| #15 | Claude Opus 5 high | Anthropic | 10.0 | 9.2 | $3.070 | 4/4 | 5.91s |
| #39 | Claude Fable 5 medium | Anthropic | 10.0 | 8.6 | $3.004 | 4/4 | 6.20s |
| #82 | Claude Opus 4.6 medium | Anthropic | 6.4 | 7.7 | $2.961 | 2/4 | 7.45s |
| #52 | Claude Fable 5.1 medium | Anthropic | 8.2 | 8.3 | $2.909 | 3/4 | 5.18s |
| #56 | Qwen3.8 2.4T A95B low | Qwen | 10.0 | 8.1 | $2.672 | 4/4 | 22.0s |
| #136 | Claude Fable 5.1 low | Anthropic | 6.5 | 6.9 | $2.565 | 2/4 | 4.54s |
| #105 | Qwen3.8 2.4T A95B high | Qwen | 10.0 | 7.4 | $2.357 | 4/4 | 24.2s |
| #245 | Gemini 3.1 Flash Lite Preview high | 7.5 | 5.3 | $2.310 | 3/3 | 43.9s | |
| #60 | Muse Spark 1.1 high | Meta | 7.5 | 8.0 | $2.253 | 2/4 | 8.60s |
| #24 | Grok 4.5 high | X AI | 10.0 | 9.0 | $2.252 | 4/4 | 5.67s |
| #75 | Claude Sonnet 4.6 medium | Anthropic | 6.5 | 7.8 | $2.126 | 2/4 | 2.98s |