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: 总成本 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #208 | Grok Build 0.1 none | X AI | 2 | 4.0 | $0.547 | 7/19 | 28.7s |
| #118 | Claude Sonnet 5 none | Anthropic | 1 | 6.3 | $0.548 | 8/22 | 6.04s |
| #58 | GPT-5.3 Chat none | OpenAI | 2 | 7.5 | $0.571 | 13/22 | 6.88s |
| #31 | Gemini 3.5 Flash-Lite high | 1 | 8.1 | $0.584 | 14/22 | 9.48s | |
| #81 | Kimi K2.5 medium | Moonshot AI | 2 | 7.0 | $0.600 | 10/22 | 99.0s |
| #34 | GPT-5.2 Chat none | OpenAI | 1 | 8.0 | $0.604 | 14/22 | 7.65s |
| #12 | Gemini 3.5 Flash medium | 1 | 9.1 | $0.642 | 19/22 | 8.20s | |
| #28 | Gemini 2.5 Flash medium | 1 | 8.2 | $0.643 | 15/22 | 21.2s | |
| #110 | Gemini 3.1 Flash Lite Preview low | 1 | 6.5 | $0.646 | 13/22 | 16.7s | |
| #27 | Muse Spark 1.1 low | Meta | 2 | 8.3 | $0.647 | 13/22 | 11.5s |
| #67 | Claude Sonnet 4.6 none | Anthropic | 1 | 7.3 | $0.661 | 12/22 | 8.12s |
| #140 | Mimo V2 Omni medium | Xiaomi | 2 | 5.9 | $0.683 | 10/21 | 41.2s |
| #89 | Qwen3.6 Flash medium | Qwen | 1 | 6.9 | $0.738 | 12/22 | 44.7s |
| #56 | Kimi K2.7 Code medium | Moonshot AI | 1 | 7.5 | $0.740 | 12/22 | 84.2s |
| #94 | Qwen3.6 35B A3B medium | Qwen | 1 | 6.7 | $0.746 | 13/22 | 58.1s |