指令遵循 排名
看看哪些 AI 模型在 指令遵循 上表现最好，哪些更稳定，以及差距主要出现在哪里。 排序方式: 指标 ↑.
455/455
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 | 指令遵循 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #251 | MiMo-V2.5-Pro medium | Xiaomi | 1.0 | 0.6 | $0.332 | 2/2 | 2.77s |
| #271 | KAT-Coder-Pro V2.5 medium | Kwaipilot | 1.0 | 0.6 | $0.669 | 2/2 | 2.58s |
| #292 | gpt-oss-120b medium | OpenAI | 1.0 | 0.6 | $0.030 | 2/2 | 7.63s |
| #324 | GLM 5V Turbo medium | Z.ai | 1.0 | 0.5 | $0.457 | 2/2 | 3.74s |
| #340 | Inkling Small low | Thinkingmachines | 1.0 | 0.5 | $0.055 | 2/2 | 1.89s |
| #344 | Mimo V2 PRO medium | Xiaomi | 1.0 | 0.5 | $0.333 | 2/2 | 3.36s |
| #390 | KAT Coder AIR V2.5 default | Kwaipilot | 1.0 | 0.4 | $0.070 | 2/2 | 1.75s |
| #404 | Hunter Alpha medium | OpenRouter | 1.0 | 0.4 | $0.000 | 2/2 | 4.18s |
| #1 | Gemini 3.6 Flash high | 1.0 | 1.0 | $0.900 | 2/2 | 4.07s | |
| #2 | Gemini 3.8 Flash high | 1.0 | 1.0 | $1.927 | 2/2 | 4.73s | |
| #3 | GPT-6 Sol high | OpenAI | 1.0 | 1.0 | $0.921 | 2/2 | 15.6s |
| #4 | GPT-6.1 Sol max | OpenAI | 1.0 | 1.0 | $1.006 | 2/2 | 5.54s |
| #5 | GPT-6 Astra max | OpenAI | 1.0 | 1.0 | $5.044 | 2/2 | 6.34s |
| #6 | GPT-6.1 Sol xhigh | OpenAI | 1.0 | 1.0 | $1.377 | 2/2 | 3.78s |
| #7 | GPT-6 Astra high | OpenAI | 1.0 | 1.0 | $4.458 | 2/2 | 3.58s |