未遵循指令 失败
看看哪些 AI 模型最常遇到 未遵循指令，让你在选择前先发现稳定性风险。 排序方式: 总成本 ↑.
293/293
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 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #184 | GPT-5.2 Chat default | OpenAI | 1 | 0.7 | $0.594 | 13/23 | 7.43s |
| #54 | Muse Spark Open low | Meta | 2 | 0.9 | $0.600 | 16/23 | 21.6s |
| #63 | DeepSeek V4.1 Flash high | DeepSeek | 1 | 0.9 | $0.617 | 16/23 | 33.3s |
| #117 | GLM 5.3 FlashX max | Z.ai | 1 | 0.8 | $0.623 | 15/23 | 44.0s |
| #222 | LongCat 2.0 low | Meituan | 1 | 0.7 | $0.630 | 10/23 | 115.0s |
| #283 | Claude Sonnet 4.6 none | Anthropic | 1 | 0.6 | $0.661 | 12/22 | 7.67s |
| #268 | KAT-Coder-Pro V2.5 medium | Kwaipilot | 1 | 0.6 | $0.669 | 11/23 | 23.9s |
| #274 | Beam 1.0 501B A23B high | Reflection | 2 | 0.6 | $0.674 | 11/23 | 9.03s |
| #164 | Gemini 2.5 Flash medium | 2 | 0.7 | $0.680 | 15/23 | 20.5s | |
| #364 | Mimo V2 Omni medium | Xiaomi | 2 | 0.5 | $0.683 | 10/21 | 41.2s |
| #309 | GPT-5.4 none | OpenAI | 1 | 0.6 | $0.690 | 7/23 | 3.89s |
| #252 | Qwen3.5-35B-A3B medium | Qwen | 1 | 0.6 | $0.716 | 11/23 | 111.5s |
| #255 | Gemini 3.1 Flash Lite Preview low | 1 | 0.6 | $0.736 | 14/23 | 19.0s | |
| #355 | Grok 4.20 Beta medium | X AI | 1 | 0.5 | $0.750 | 14/18 | 9.75s |
| #100 | DeepSeek V4.1 Flash 1017 max | DeepSeek | 2 | 0.8 | $0.757 | 15/23 | 78.2s |