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: 失败次数 ↑.
215/215
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） |
|---|---|---|---|---|---|---|---|
| #116 | GLM 5.3 Flash high | Z.ai | 1 | 7.3 | $0.029 | 13/22 | 25.4s |
| #117 | Gemini 3.1 Flash Lite medium | 1 | 7.3 | $0.120 | 13/22 | 4.38s | |
| #118 | Qwen3.7 Plus none | Qwen | 1 | 7.3 | $0.106 | 12/22 | 12.1s |
| #120 | Claude Opus 4.8 none | Anthropic | 1 | 7.3 | $1.166 | 13/22 | 4.92s |
| #126 | Muse Glimmer 30B medium | Meta | 1 | 7.2 | $0.211 | 11/22 | 30.6s |
| #132 | GPT-5.6 Sol none | OpenAI | 1 | 7.0 | $0.201 | 12/22 | 2.17s |
| #133 | DeepSeek V3.2 medium | DeepSeek | 1 | 7.0 | $0.078 | 11/22 | 68.4s |
| #138 | Seed-2.0-Mini medium | Bytedance Seed | 1 | 7.0 | $0.116 | 11/22 | 93.1s |
| #140 | KAT-Coder-Pro V2.5 medium | Kwaipilot | 1 | 6.9 | $0.478 | 11/22 | 24.9s |
| #143 | Seed-2.0-Code high | Bytedance Seed | 1 | 6.9 | $1.273 | 11/22 | 124.2s |
| #145 | Qwen3.6 Flash medium | Qwen | 1 | 6.8 | $0.741 | 12/22 | 45.0s |
| #147 | Seed-2.0-Code medium | Bytedance Seed | 1 | 6.8 | $1.153 | 10/22 | 101.1s |
| #151 | GLM 5.3 low | Z.ai | 1 | 6.8 | $0.257 | 12/22 | 13.6s |
| #155 | GLM 5.2 none | Z.ai | 1 | 6.7 | $0.153 | 13/22 | 9.65s |
| #157 | LongCat 2.0 low | Meituan | 1 | 6.7 | $0.412 | 10/22 | 113.6s |