指令遵循：未遵循指令
指令遵循
未遵循指令
看看哪些 AI 模型在 指令遵循 上最容易遇到 未遵循指令，更快找出薄弱点。
77/77
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 | 分类得分 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #34 | Claude Sonnet 5.5 max | Anthropic | 1 | 0.9 | $8.557 | 1/2 | 6.24s |
| #40 | Muse Spark 1.3 high | Meta | 1 | 0.7 | $1.891 | 1/2 | 14.7s |
| #54 | Muse Spark Open low | Meta | 1 | 0.8 | $0.600 | 1/2 | 10.3s |
| #57 | Muse Spark 1.1 medium | Meta | 1 | 0.7 | $1.665 | 1/2 | 6.31s |
| #62 | Muse Spark Open medium | Meta | 1 | 0.7 | $1.260 | 1/2 | 18.4s |
| #68 | MiMo-V2.6-Pro medium | Xiaomi | 1 | 0.8 | $0.586 | 1/2 | 1.79s |
| #72 | Muse Spark 1.1 low | Meta | 1 | 0.7 | $0.885 | 1/2 | 5.42s |
| #82 | Nemotron 3.5 Super VL high | NVIDIA | 1 | 0.8 | $0.349 | 1/2 | 6.10s |
| #85 | Muse Glimmer 30B xhigh | Meta | 1 | 0.8 | $0.585 | 1/2 | 8.90s |
| #88 | Muse Spark 1.1 high | Meta | 1 | 0.6 | $2.570 | 1/2 | 7.81s |
| #106 | DeepSeek V4 Pro 0423 high | DeepSeek | 1 | 0.8 | $0.149 | 1/2 | 8.73s |
| #124 | Muse Wonder max | Meta | 1 | 0.8 | $4.766 | 1/2 | 13.2s |
| #135 | GPT-6 Luna high | OpenAI | 1 | 0.8 | $0.074 | 1/2 | 1.92s |
| #136 | Muse Glimmer 30B high | Meta | 1 | 0.8 | $0.506 | 1/2 | 8.62s |
| #140 | Qwen3.7 Flash low | Qwen | 1 | 0.8 | $0.071 | 1/2 | 9.88s |