通用智能：未遵循指令
通用智能
未遵循指令
看看哪些 AI 模型在 通用智能 上最容易遇到 未遵循指令，更快找出薄弱点。
142/142
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） |
|---|---|---|---|---|---|---|---|
| #182 | MiMo-V2.6-Flash low | Xiaomi | 1 | 0.5 | $0.200 | 0/1 | 1.60s |
| #183 | MiMo-V2.5 medium | Xiaomi | 1 | 0.5 | $0.130 | 0/1 | 5.37s |
| #184 | GPT-5.2 Chat default | OpenAI | 1 | 0.4 | $0.594 | 0/1 | 3.20s |
| #193 | Muse Glimmer 30B low | Meta | 1 | 0.5 | $0.219 | 0/1 | 2.50s |
| #199 | Claude Sonnet 5.5 low | Anthropic | 1 | 0.5 | $0.909 | 0/1 | 2.33s |
| #202 | Qwen3.5-Flash medium | Qwen | 1 | 0.6 | $0.184 | 0/1 | 40.1s |
| #204 | Mercury 2.5 Preview medium | Inception | 1 | 0.5 | $0.039 | 0/1 | 2.09s |
| #206 | Space Bunny Alpha max | Stealth | 1 | 0.5 | $0.000 | 0/1 | 8.15s |
| #207 | Solar Pro 4 xhigh | Upstage | 1 | 0.6 | $0.067 | 0/1 | 61.9s |
| #212 | Grok 4.7 high | X AI | 1 | 0.4 | $3.037 | 0/1 | 17.1s |
| #213 | MiniMax M3 medium | Minimax | 1 | 0.5 | $0.422 | 0/1 | 33.3s |
| #215 | GPT 5.3 Chat default | OpenAI | 1 | 0.5 | $0.533 | 0/1 | 1.99s |
| #218 | GLM 5.3 Flash low | Z.ai | 1 | 0.5 | $0.038 | 0/1 | 1.68s |
| #221 | Qwen3.7 Flash medium | Qwen | 1 | 0.6 | $0.076 | 0/1 | 10.2s |
| #223 | Mercury 2 medium | Inception | 1 | 0.5 | $0.121 | 0/1 | 821ms |