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: 分数 ↑.
141/141
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） |
|---|---|---|---|---|---|---|---|
| #126 | Gemini 3.1 Flash Lite minimal | 3 | 6.1 | $0.047 | 10/22 | 1.86s | |
| #123 | GPT-5.6 Luna low | OpenAI | 1 | 6.2 | $0.249 | 10/22 | 5.04s |
| #121 | Gemma 4 31B none | 1 | 6.2 | $0.021 | 10/22 | 5.34s | |
| #120 | Qwen3.5-Flash medium | Qwen | 1 | 6.2 | $0.139 | 12/22 | 84.8s |
| #119 | MiMo-V2-Flash medium | Xiaomi | 1 | 6.3 | $0.043 | 12/21 | 20.1s |
| #118 | Claude Sonnet 5 none | Anthropic | 1 | 6.3 | $0.548 | 8/22 | 6.04s |
| #115 | Mimo V2 PRO medium | Xiaomi | 1 | 6.3 | $0.333 | 12/21 | 22.2s |
| #114 | Ring-2.6-1T medium | Inclusionai | 2 | 6.3 | $0.103 | 11/22 | 68.7s |
| #112 | Gemini 3.1 Flash Lite Preview none | 2 | 6.4 | $0.052 | 12/22 | 1.58s | |
| #110 | Gemini 3.1 Flash Lite Preview low | 1 | 6.5 | $0.646 | 13/22 | 16.7s | |
| #109 | Qwen3.5-27B none | Qwen | 2 | 6.5 | $0.090 | 8/22 | 4.76s |
| #107 | MiMo-V2.5 medium | Xiaomi | 1 | 6.5 | $0.082 | 12/22 | 32.2s |
| #106 | Hy3 preview medium | Tencent | 1 | 6.5 | $0.018 | 14/21 | 16.3s |
| #105 | Qwen3.6 27B medium | Qwen | 1 | 6.5 | $0.779 | 10/22 | 106.3s |
| #102 | LongCat 2.0 high | Meituan | 2 | 6.6 | $0.469 | 9/22 | 148.7s |