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。
115/115
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） |
|---|---|---|---|---|---|---|---|
| #259 | MiniMax M2.7 medium | Minimax | 1 | 3.9 | $0.208 | 0/1 | 38.7s |
| #260 | Mercury 2.5 Preview low | Inception | 1 | 5.0 | $0.011 | 0/1 | 1.05s |
| #271 | GPT-5.4 Nano none | OpenAI | 1 | 3.8 | $0.041 | 0/1 | 1.31s |
| #272 | Trinity Large Thinking high | Arcee AI | 1 | 6.5 | $0.592 | 0/1 | 12.9s |
| #273 | Grok 4.20 Multi Agent Beta medium | X AI | 1 | 5.8 | $5.599 | 0/1 | 6.40s |
| #276 | Trinity Large Preview none | Arcee AI | 1 | 4.5 | $0.008 | 0/1 | 873ms |
| #277 | Hunter Alpha medium | OpenRouter | 1 | 7.0 | $0.000 | 0/1 | 6.44s |
| #278 | Grok 4.1 Fast medium | X AI | 1 | 4.2 | $0.069 | 0/1 | 16.2s |
| #280 | Cobuddy medium | Baidu | 1 | 4.2 | $0.000 | 0/1 | 23.2s |
| #281 | Mercury 2 none | Inception | 1 | 4.8 | $0.030 | 0/1 | 628ms |
| #283 | Qwen3 Coder Next medium | Qwen | 1 | 6.3 | $0.034 | 0/1 | 1.39s |
| #284 | MiniMax M2.5 medium | Minimax | 1 | 3.8 | $0.327 | 0/1 | 6.63s |
| #286 | Grok 4.20 Beta none | X AI | 1 | 5.0 | $0.087 | 0/1 | 541ms |
| #288 | Elephant Alpha none | Openrouter | 1 | 4.0 | $0.000 | 0/1 | 854ms |
| #290 | Elephant Alpha medium | Openrouter | 1 | 4.3 | $0.000 | 0/1 | 920ms |