反AI技巧:未遵循指令
反AI技巧
未遵循指令
看看哪些 AI 模型在 反AI技巧 上最容易遇到 未遵循指令,更快找出薄弱点。 排序方式: 总成本 ↓.
49/49
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 | 未遵循指令 次数 | 分类得分 | 总成本 | 测试正确 | 响应时间(平均) |
|---|---|---|---|---|---|---|---|
| #87 | Muse Spark 1.1 high | Meta | 1 | 0.7 | $2.570 | 2/4 | 8.60s |
| #54 | Muse Spark 1.2 high | Meta | 2 | 0.7 | $2.018 | 2/4 | 6.00s |
| #196 | Kimi K2.6 medium | Moonshot AI | 1 | 0.7 | $1.594 | 2/4 | 11.6s |
| #55 | Muse Spark 1.2 medium | Meta | 1 | 0.7 | $1.590 | 2/4 | 5.38s |
| #65 | GPT-5.2 medium | OpenAI | 1 | 0.7 | $1.558 | 2/4 | 7.81s |
| #194 | Claude Sonnet 5.5 low | Anthropic | 1 | 0.7 | $0.909 | 2/4 | 2.55s |
| #64 | Muse Spark 1.2 low | Meta | 1 | 0.9 | $0.881 | 3/4 | 3.26s |
| #162 | LongCat 2.0 high | Meituan | 1 | 0.9 | $0.778 | 3/4 | 7.76s |
| #266 | Beam 1.0 501B A23B high | Reflection | 1 | 0.9 | $0.674 | 3/4 | 1.36s |
| #53 | Muse Spark Open low | Meta | 1 | 0.9 | $0.600 | 3/4 | 10.5s |
| #126 | Step 3.7 Flash medium | Stepfun | 1 | 0.9 | $0.571 | 3/4 | 9.65s |
| #210 | GPT 5.3 Chat default | OpenAI | 1 | 0.7 | $0.533 | 2/4 | 3.86s |
| #312 | GLM 5V Turbo medium | Z.ai | 1 | 0.7 | $0.457 | 2/4 | 10.8s |
| #384 | MiniMax M2.5 medium | Minimax | 1 | 0.8 | $0.440 | 2/4 | 20.8s |
| #208 | MiniMax M3 medium | Minimax | 1 | 0.6 | $0.422 | 1/4 | 14.9s |