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: 分数 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #102 | GPT-5.4 Mini medium | OpenAI | 3 | 7.5 | $0.786 | 12/22 | 26.7s |
| #101 | Mercury 2.5 Preview medium | Inception | 1 | 7.5 | $0.024 | 15/22 | 3.58s |
| #100 | Qwen3.5-27B medium | Qwen | 2 | 7.5 | $0.982 | 13/22 | 113.3s |
| #98 | GPT 5.3 Chat none | OpenAI | 2 | 7.5 | $0.533 | 13/22 | 6.56s |
| #97 | MiniMax M3 medium | Minimax | 2 | 7.5 | $0.300 | 11/22 | 75.2s |
| #95 | GPT-5.4 Nano medium | OpenAI | 2 | 7.5 | $0.142 | 12/22 | 13.3s |
| #92 | Solar Pro 4 xhigh | Upstage | 3 | 7.6 | $0.050 | 12/22 | 134.9s |
| #90 | GLM 5 Turbo medium | Z.ai | 1 | 7.6 | $0.323 | 14/21 | 23.0s |
| #89 | DeepSeek V4 Flash 0423 high | DeepSeek | 2 | 7.6 | $0.042 | 13/22 | 51.8s |
| #88 | DeepSeek V4 Pro high | DeepSeek | 2 | 7.7 | $0.476 | 10/22 | 92.5s |
| #87 | Claude Opus 4.6 medium | Anthropic | 1 | 7.7 | $2.961 | 13/22 | 32.2s |
| #86 | Seed-2.0-Code low | Bytedance Seed | 1 | 7.7 | $0.767 | 13/22 | 72.2s |
| #85 | GLM 5 medium | Z.ai | 1 | 7.7 | $0.228 | 15/21 | 33.5s |
| #84 | Qwen3.7 Flash high | Qwen | 1 | 7.8 | $0.052 | 13/22 | 41.4s |
| #82 | Seed-2.0-Lite medium | Bytedance Seed | 2 | 7.8 | $0.236 | 13/22 | 47.9s |