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 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #178 | MiMo-V2.5 medium | Xiaomi | 1 | 6.4 | $0.104 | 11/22 | 46.3s |
| #180 | Ring-2.6-1T medium | Inclusionai | 2 | 6.4 | $0.102 | 11/22 | 68.8s |
| #192 | Qwen3.5-Flash medium | Qwen | 1 | 6.1 | $0.142 | 11/22 | 84.4s |
| #315 | Step 3.5 Flash none | Stepfun | 1 | 2.3 | $0.020 | 6/12 | 39.0s |
| #159 | GLM 5V Turbo medium | Z.ai | 1 | 6.7 | $0.457 | 11/21 | 23.1s |
| #62 | GPT-5 Mini medium | OpenAI | 3 | 8.1 | $0.241 | 12/22 | 27.6s |
| #65 | Muse Spark 1.1 high | Meta | 2 | 8.0 | $2.253 | 12/22 | 36.9s |
| #92 | Solar Pro 4 xhigh | Upstage | 3 | 7.6 | $0.050 | 12/22 | 134.9s |
| #95 | GPT-5.4 Nano medium | OpenAI | 2 | 7.5 | $0.142 | 12/22 | 13.3s |
| #102 | GPT-5.4 Mini medium | OpenAI | 3 | 7.5 | $0.786 | 12/22 | 26.7s |
| #113 | Claude Sonnet 4.6 none | Anthropic | 1 | 7.3 | $0.661 | 12/22 | 7.67s |
| #118 | Qwen3.7 Plus none | Qwen | 1 | 7.3 | $0.106 | 12/22 | 12.1s |
| #121 | Kimi K2.6 medium | Moonshot AI | 2 | 7.2 | $1.247 | 12/22 | 115.9s |
| #131 | Grok 4.3 medium | X AI | 2 | 7.0 | $0.741 | 12/22 | 44.2s |
| #132 | GPT-5.6 Sol none | OpenAI | 1 | 7.0 | $0.201 | 12/22 | 2.17s |