AI BENCHY 分类
领域专项 排名
看看哪些 AI 模型在 领域专项 上表现最好，哪些更稳定，以及差距主要出现在哪里。
| 排名 | 模型 | 公司 | 领域专项 得分 | 分数 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|
| #33 | GLM 5.1 medium | Z.ai | 5.3 | 7.8 | 1/3 | 29.8s |
| #47 | Grok 4.20 medium | X AI | 5.3 | 7.0 | 1/3 | 27.0s |
| #49 | Qwen3.5 Plus 2026-02-15 none | Qwen | 5.3 | 6.8 | 1/3 | 1.17s |
| #55 | MiMo-V2-Omni none | Xiaomi | 5.3 | 6.5 | 1/3 | 1.14s |
| #58 | GLM 5V Turbo none | Z.ai | 5.3 | 6.2 | 1/3 | 2.09s |
| #70 | Qwen3.5-122B-A10B none | Qwen | 5.3 | 5.7 | 1/3 | 465ms |
| #72 | Hunter Alpha none | OpenRouter | 5.3 | 5.7 | 1/3 | 2.33s |
| #76 | Kimi K2.5 none | Moonshot AI | 5.3 | 5.5 | 1/3 | 4.38s |
| #77 | GLM 5 Turbo none | Z.ai | 5.3 | 5.5 | 1/3 | 1.97s |
| #78 | Trinity Large Preview none | Arcee AI | 5.3 | 5.3 | 1/3 | 877ms |
| #83 | Mistral Small 4 none | Mistral | 5.3 | 5.2 | 1/3 | 367ms |
| #87 | Qwen3 Coder Next none | Qwen | 5.3 | 5.1 | 1/3 | 962ms |
| #92 | Qwen3 Coder Next medium | Qwen | 5.3 | 4.7 | 1/3 | 638ms |
| #5 | Gemini 3 Flash Preview low | 5.3 | 8.8 | 1/3 | 8.05s | |
| #16 | GPT-5.4 medium | OpenAI | 5.3 | 8.2 | 1/3 | 74.3s |