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: 测试正确 ↓.
210/210
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） |
|---|---|---|---|---|---|---|---|
| #17 | Claude Fable 5 medium | Anthropic | 10.0 | 8.6 | $3.478 | 2/2 | 5.90s |
| #18 | GPT-5.4 medium | OpenAI | 10.0 | 8.5 | $1.533 | 2/2 | 3.11s |
| #19 | Qwen3.6 Max Preview medium | Qwen | 10.0 | 8.4 | $1.143 | 2/2 | 24.3s |
| #20 | Grok 4.5 low | X AI | 9.8 | 8.4 | $0.935 | 2/2 | 2.80s |
| #21 | GPT-5.2 medium | OpenAI | 9.9 | 8.4 | $0.951 | 2/2 | 3.12s |
| #22 | Grok 4.5 medium | X AI | 9.8 | 8.3 | $1.928 | 2/2 | 6.06s |
| #23 | Claude Sonnet 5 medium | Anthropic | 9.9 | 8.3 | $0.922 | 2/2 | 3.10s |
| #25 | Gemini 2.5 Flash medium | 9.8 | 8.2 | $0.643 | 2/2 | 2.62s | |
| #26 | GPT-5 Mini medium | OpenAI | 10.0 | 8.1 | $0.237 | 2/2 | 11.6s |
| #28 | Inkling high | Thinkingmachines | 9.8 | 8.0 | $1.006 | 2/2 | 7.00s |
| #29 | Step 3.7 Flash medium | Stepfun | 9.8 | 8.0 | $0.515 | 2/2 | 1.83s |
| #30 | GPT-5.2 Chat none | OpenAI | 9.8 | 8.0 | $0.604 | 2/2 | 5.51s |
| #31 | GLM 5.2 high | Z.ai | 10.0 | 8.0 | $0.970 | 2/2 | 4.26s |
| #32 | Inkling medium | Thinkingmachines | 9.8 | 8.0 | $0.391 | 2/2 | 6.17s |
| #33 | Kimi K3 max | Moonshot AI | 10.0 | 8.0 | $3.112 | 2/2 | 7.66s |