AI BENCHY 分类
常识问答 排名
看看哪些 AI 模型在 常识问答 上表现最好，哪些更稳定，以及差距主要出现在哪里。
169/169
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 | 常识问答 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #47 | Qwen3.6 Flash medium | Qwen | 3.0 | 7.5 | $0.288 | 0/1 | 122.9s |
| #48 | DeepSeek V3.2 medium | DeepSeek | 3.0 | 7.5 | $0.044 | 0/1 | 84.0s |
| #49 | Claude Opus 4.7 none | Anthropic | 3.0 | 7.4 | $0.505 | 0/1 | 1.46s |
| #50 | Seed-2.0-Mini medium | Bytedance Seed | 3.0 | 7.4 | $0.044 | 0/1 | 56.8s |
| #51 | MiMo-V2.5-Pro medium | Xiaomi | 3.0 | 7.4 | $0.106 | 0/1 | 12.5s |
| #53 | Grok 4.20 medium | X AI | 3.0 | 7.3 | $0.609 | 0/1 | 63.5s |
| #54 | Hy3 preview medium | Tencent | 3.0 | 7.3 | $0.021 | 0/1 | 39.9s |
| #55 | Claude Sonnet 4.6 none | Anthropic | 3.0 | 7.3 | $0.316 | 0/1 | 4.67s |
| #56 | GLM 5V Turbo medium | Z.ai | 3.0 | 7.3 | $0.457 | 0/1 | 41.0s |
| #57 | Claude Opus 4.8 none | Anthropic | 3.0 | 7.2 | $0.539 | 0/1 | 3.41s |
| #58 | DeepSeek V4 Pro none | DeepSeek | 3.0 | 7.2 | $0.034 | 0/1 | 5.76s |
| #59 | Gemma 4 26B A4B medium | 3.0 | 7.2 | $0.045 | 0/1 | 180.9s | |
| #60 | Qwen3.7 Plus none | Qwen | 3.0 | 7.2 | $0.023 | 0/1 | 1.21s |
| #61 | GLM 5.2 none | Z.ai | 3.0 | 7.1 | $0.076 | 0/1 | 3.41s |
| #62 | MiMo-V2-Flash medium | Xiaomi | 3.0 | 7.1 | $0.043 | 0/1 | 1.96s |