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: 测试正确 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #158 | DeepSeek V4 Pro 0423 none | DeepSeek | 2 | 0.7 | $0.083 | 10/23 | 14.1s |
| #165 | LongCat 2.0 high | Meituan | 2 | 0.7 | $0.778 | 10/23 | 151.7s |
| #168 | Qwen3.5-27B none | Qwen | 2 | 0.7 | $0.116 | 10/23 | 9.98s |
| #189 | Step 5 Preview high | Stepfun | 1 | 0.7 | $4.513 | 10/23 | 154.4s |
| #199 | Claude Sonnet 5.5 low | Anthropic | 5 | 0.7 | $0.909 | 10/23 | 7.46s |
| #221 | Qwen3.7 Flash medium | Qwen | 4 | 0.7 | $0.076 | 10/23 | 51.8s |
| #222 | LongCat 2.0 low | Meituan | 1 | 0.7 | $0.630 | 10/23 | 115.0s |
| #223 | Mercury 2 medium | Inception | 3 | 0.7 | $0.121 | 10/23 | 4.40s |
| #243 | Minimax M3.1 Flash xhigh | Minimax | 2 | 0.6 | $0.000 | 10/23 | 21.7s |
| #244 | Kimi K2.5 medium | Moonshot AI | 2 | 0.6 | $0.841 | 10/23 | 125.8s |
| #249 | Dots 3 Note Preview high | Dots Studio | 1 | 0.6 | $0.000 | 10/23 | 70.5s |
| #250 | Dots 3 Note Preview low | Dots Studio | 2 | 0.6 | $0.000 | 10/23 | 66.1s |
| #262 | Space Bunny Alpha medium | Stealth | 1 | 0.6 | $0.000 | 10/23 | 32.9s |
| #279 | Step 5 Preview medium | Stepfun | 2 | 0.6 | $4.136 | 10/23 | 136.1s |
| #286 | Inkling Small medium | Thinkingmachines | 4 | 0.6 | $0.113 | 10/23 | 6.03s |