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 ↓.
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） |
|---|---|---|---|---|---|---|---|
| #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 |
| #148 | Solar Pro 4 low | Upstage | 2 | 6.8 | $0.044 | 11/22 | 136.1s |
| #149 | Solar Pro 4 medium | Upstage | 2 | 6.8 | $0.047 | 12/22 | 127.6s |
| #150 | DeepSeek V4 Pro none | DeepSeek | 2 | 6.8 | $0.220 | 9/22 | 11.7s |
| #151 | GLM 5.3 low | Z.ai | 1 | 6.8 | $0.257 | 12/22 | 13.6s |
| #152 | MiMo-V2.5-Pro medium | Xiaomi | 2 | 6.8 | $0.221 | 11/22 | 48.7s |
| #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 |
| #158 | Gemini 3.5 Flash minimal | 1 | 6.7 | $0.300 | 13/22 | 2.65s | |
| #159 | GLM 5V Turbo medium | Z.ai | 1 | 6.7 | $0.457 | 11/21 | 23.1s |
| #160 | LongCat 2.0 high | Meituan | 2 | 6.7 | $0.492 | 9/22 | 153.3s |
| #162 | Gemini 3.5 Flash Lite low | 1 | 6.6 | $0.138 | 12/22 | 2.56s | |
| #163 | Qwen3.5-27B none | Qwen | 2 | 6.6 | $0.058 | 9/22 | 4.77s |