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 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #55 | Muse Spark 1.2 high | Meta | 3 | 0.9 | $2.018 | 15/23 | 28.1s |
| #56 | Muse Spark 1.2 medium | Meta | 3 | 0.9 | $1.590 | 15/23 | 21.3s |
| #65 | Muse Spark 1.2 low | Meta | 3 | 0.9 | $0.881 | 16/23 | 11.8s |
| #66 | GPT-5.2 medium | OpenAI | 3 | 0.9 | $1.558 | 15/23 | 31.3s |
| #72 | Muse Spark 1.1 low | Meta | 3 | 0.9 | $0.885 | 14/23 | 13.2s |
| #84 | GPT-5 Mini medium | OpenAI | 3 | 0.8 | $0.315 | 13/23 | 29.4s |
| #119 | GPT-5.4 Mini medium | OpenAI | 3 | 0.8 | $1.102 | 13/23 | 29.9s |
| #136 | Muse Glimmer 30B high | Meta | 3 | 0.8 | $0.506 | 11/23 | 69.9s |
| #140 | Qwen3.7 Flash low | Qwen | 3 | 0.8 | $0.071 | 12/23 | 41.0s |
| #193 | Muse Glimmer 30B low | Meta | 3 | 0.7 | $0.219 | 11/23 | 22.4s |
| #207 | Solar Pro 4 xhigh | Upstage | 3 | 0.7 | $0.067 | 12/23 | 142.8s |
| #223 | Mercury 2 medium | Inception | 3 | 0.7 | $0.121 | 10/23 | 4.40s |
| #227 | Claude Sonnet 5.5 medium | Anthropic | 3 | 0.7 | $1.100 | 9/23 | 8.03s |
| #256 | Minimax M3.1 Flash medium | Minimax | 3 | 0.6 | $0.000 | 8/23 | 19.5s |
| #258 | Solar Pro 4 high | Upstage | 3 | 0.6 | $0.077 | 11/23 | 128.9s |