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: 失败次数 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #294 | GLM 4.7 Flash medium | Z.ai | 2 | 4.3 | $0.168 | 4/22 | 134.3s |
| #295 | Elephant Alpha medium | Openrouter | 2 | 4.3 | $0.000 | 6/21 | 1.27s |
| #297 | Hunter Alpha none | OpenRouter | 2 | 4.2 | $0.000 | 6/18 | 4.70s |
| #301 | MiMo-V2-Flash none | Xiaomi | 2 | 4.0 | $0.025 | 4/21 | 2.76s |
| #305 | Grok Build 0.1 none | X AI | 2 | 4.0 | $0.547 | 7/19 | 28.7s |
| #312 | gpt-oss-120b none | OpenAI | 2 | 3.7 | $0.010 | 6/19 | 21.6s |
| #314 | Nemotron 3 Nano Omni 30b A3b Reasoning none | NVIDIA | 2 | 3.2 | $0.000 | 2/19 | 728ms |
| #41 | Muse Spark 1.2 high | Meta | 3 | 8.7 | $1.771 | 14/22 | 26.6s |
| #42 | Muse Spark 1.2 medium | Meta | 3 | 8.6 | $1.339 | 14/22 | 19.7s |
| #49 | Muse Spark 1.2 low | Meta | 3 | 8.4 | $0.655 | 15/22 | 9.77s |
| #52 | GPT-5.2 medium | OpenAI | 3 | 8.4 | $1.182 | 14/22 | 28.5s |
| #56 | Muse Spark 1.1 low | Meta | 3 | 8.3 | $0.673 | 13/22 | 11.9s |
| #62 | GPT-5 Mini medium | OpenAI | 3 | 8.1 | $0.241 | 12/22 | 27.6s |
| #92 | Solar Pro 4 xhigh | Upstage | 3 | 7.6 | $0.050 | 12/22 | 134.9s |
| #102 | GPT-5.4 Mini medium | OpenAI | 3 | 7.5 | $0.786 | 12/22 | 26.7s |