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。
133/133
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 | 答案错误 次数 | 分类得分 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #59 | Gemma 4 26B A4B medium | 1 | 3.0 | $0.045 | 0/1 | 180.9s | |
| #60 | Qwen3.7 Plus none | Qwen | 1 | 3.0 | $0.023 | 0/1 | 1.21s |
| #61 | GLM 5.2 none | Z.ai | 1 | 3.0 | $0.076 | 0/1 | 3.41s |
| #62 | MiMo-V2-Flash medium | Xiaomi | 1 | 3.0 | $0.043 | 0/1 | 1.96s |
| #64 | GLM 5.1 medium | Z.ai | 1 | 3.0 | $0.292 | 0/1 | 29.4s |
| #65 | Kimi K2.7 Code medium | Moonshot AI | 1 | 3.0 | $0.583 | 0/1 | 341.8s |
| #66 | Gemini 3.5 Flash none | 1 | 2.8 | $1.079 | 0/1 | 4.87s | |
| #67 | Gemini 3 Flash Preview none | 1 | 3.0 | $0.025 | 0/1 | 1.07s | |
| #68 | Qwen3.7 Max none | Qwen | 1 | 3.0 | $0.054 | 0/1 | 856ms |
| #70 | Qwen3.5-Flash medium | Qwen | 1 | 3.0 | $0.080 | 0/1 | 49.0s |
| #71 | Gemini 3.5 Flash minimal | 1 | 3.0 | $0.108 | 0/1 | 1.76s | |
| #72 | Ring-2.6-1T medium | Inclusionai | 1 | 3.0 | $0.033 | 0/1 | 113.9s |
| #73 | Mimo V2 Omni medium | Xiaomi | 1 | 3.0 | $0.683 | 0/1 | 234.2s |
| #74 | Hy3 preview high | Tencent | 1 | 3.0 | $0.059 | 0/1 | 47.7s |
| #75 | Qwen3.6 35B A3B medium | Qwen | 1 | 3.0 | $0.146 | 0/1 | 32.9s |