AI BENCHY 分类失败
常识问答：答案错误
常识问答
答案错误
看看哪些 AI 模型在 常识问答 上最容易遇到 答案错误，更快找出薄弱点。
失败原因
| 排名 | 模型 | 公司 | 答案错误 次数 | 分类得分 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|
| #90 | Qwen3.5 Plus 2026-04-20 none | Qwen | 1 | 3.0 | 0/1 | 33.3s |
| #91 | Qwen3.5-35B-A3B none | Qwen | 1 | 3.0 | 0/1 | 493ms |
| #92 | MiMo-V2-Pro none | Xiaomi | 1 | 3.0 | 0/1 | 1.63s |
| #93 | Qwen3.5-27B none | Qwen | 1 | 3.0 | 0/1 | 599ms |
| #94 | Qwen3.6 27B none | Qwen | 1 | 3.0 | 0/1 | 4.03s |
| #95 | Cobuddy medium | Baidu | 1 | 3.0 | 0/1 | 37.0s |
| #96 | Owl Alpha none | Openrouter | 1 | 3.0 | 0/1 | 2.50s |
| #97 | GLM 4.7 Flash none | Z.ai | 1 | 3.0 | 0/1 | 692ms |
| #98 | GPT-5.4 none | OpenAI | 1 | 3.0 | 0/1 | 990ms |
| #99 | gpt-oss-120b medium | OpenAI | 1 | 3.0 | 0/1 | 26.5s |
| #100 | Kimi K2.6 none | Moonshot AI | 1 | 3.0 | 0/1 | 1.36s |
| #101 | GLM 5.1 none | Z.ai | 1 | 3.0 | 0/1 | 2.34s |
| #102 | MiMo-V2.5-Pro none | Xiaomi | 1 | 3.0 | 0/1 | 1.89s |
| #104 | DeepSeek V3.2 none | DeepSeek | 1 | 3.0 | 0/1 | 17.2s |
| #105 | Qwen3.6 Flash none | Qwen | 1 | 3.0 | 0/1 | 649ms |