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 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #136 | Step 3.5 Flash medium | Stepfun | 3 | 6.0 | $0.108 | 11/21 | 174.2s |
| #29 | GPT-5 Mini medium | OpenAI | 3 | 8.1 | $0.237 | 12/22 | 27.6s |
| #30 | Muse Spark 1.1 high | Meta | 2 | 8.1 | $1.694 | 12/22 | 31.5s |
| #51 | MiniMax M3 medium | Minimax | 2 | 7.6 | $0.286 | 12/22 | 75.0s |
| #56 | Kimi K2.7 Code medium | Moonshot AI | 1 | 7.5 | $0.740 | 12/22 | 84.2s |
| #57 | GPT-5.4 Nano medium | OpenAI | 2 | 7.5 | $0.138 | 12/22 | 13.2s |
| #60 | GPT-5.4 Mini medium | OpenAI | 3 | 7.5 | $0.756 | 12/22 | 25.9s |
| #67 | Claude Sonnet 4.6 none | Anthropic | 1 | 7.3 | $0.661 | 12/22 | 8.12s |
| #72 | Kimi K2.6 medium | Moonshot AI | 2 | 7.2 | $1.036 | 12/22 | 110.0s |
| #79 | Grok 4.20 medium | X AI | 2 | 7.1 | $0.777 | 12/22 | 29.5s |
| #88 | MiMo-V2.5-Pro medium | Xiaomi | 2 | 6.9 | $0.187 | 12/22 | 33.9s |
| #89 | Qwen3.6 Flash medium | Qwen | 1 | 6.9 | $0.738 | 12/22 | 44.7s |
| #101 | GLM 5.2 none | Z.ai | 1 | 6.6 | $0.128 | 12/22 | 9.34s |
| #107 | MiMo-V2.5 medium | Xiaomi | 1 | 6.5 | $0.082 | 12/22 | 32.2s |
| #112 | Gemini 3.1 Flash Lite Preview none | 2 | 6.4 | $0.052 | 12/22 | 1.58s |