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。 排序方式: 响应时间（平均） ↓.
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） |
|---|---|---|---|---|---|---|---|
| #116 | Qwen3.5-27B medium | Qwen | 1 | 0.6 | $1.135 | 0/1 | 101.4s |
| #37 | Qwen3.8 Max (0902) high | Qwen | 1 | 0.6 | $3.306 | 0/1 | 75.1s |
| #244 | Kimi K2.5 medium | Moonshot AI | 1 | 0.6 | $0.841 | 0/1 | 69.7s |
| #207 | Solar Pro 4 xhigh | Upstage | 1 | 0.6 | $0.067 | 0/1 | 61.9s |
| #408 | Ling 3.0 Tiny high | Inclusionai | 1 | 0.5 | $0.000 | 0/1 | 60.5s |
| #379 | Owl Alpha medium | Openrouter | 1 | 0.4 | $0.000 | 0/1 | 58.6s |
| #300 | Ring 2.6 1t medium | Inclusionai | 1 | 0.4 | $0.102 | 0/1 | 58.3s |
| #34 | Claude Sonnet 5.5 max | Anthropic | 1 | 0.5 | $8.557 | 0/1 | 56.7s |
| #241 | Solar Pro 4 medium | Upstage | 1 | 0.3 | $0.098 | 0/1 | 48.0s |
| #375 | Gemini 3.1 Flash Lite high | 1 | 0.5 | $2.044 | 0/1 | 45.7s | |
| #258 | Solar Pro 4 high | Upstage | 1 | 0.6 | $0.077 | 0/1 | 42.2s |
| #69 | Seed 2.1 Turbo medium | Bytedance Seed | 1 | 0.6 | $2.042 | 0/1 | 40.6s |
| #202 | Qwen3.5-Flash medium | Qwen | 1 | 0.6 | $0.184 | 0/1 | 40.1s |
| #177 | Qwen3.6 27B medium | Qwen | 1 | 0.6 | $1.021 | 0/1 | 39.5s |
| #351 | MiniMax M2.7 medium | Minimax | 1 | 0.4 | $0.326 | 0/1 | 38.7s |