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。
| 排名 | 模型 | 公司 | 常识问答 得分 | 分数 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|
| #1 | Gemini 3 Flash Preview medium | 10.0 | 9.8 | 1/1 | 5.50s | |
| #2 | Gemini 3.5 Flash high | 10.0 | 9.6 | 1/1 | 3.94s | |
| #3 | Gemini 3.5 Flash low | 10.0 | 9.4 | 1/1 | 1.88s | |
| #4 | Gemini 3.1 Pro Preview medium | 10.0 | 9.4 | 1/1 | 6.27s | |
| #7 | Gemini 3.5 Flash medium | 10.0 | 9.0 | 1/1 | 2.75s | |
| #16 | Gemini 3 Flash Preview low | 10.0 | 8.4 | 1/1 | 2.75s | |
| #5 | Qwen3.7 Max medium | Qwen | 3.0 | 9.1 | 0/1 | 33.4s |
| #6 | GPT-5.5 low | OpenAI | 3.0 | 9.0 | 0/1 | 10.1s |
| #8 | Claude Opus 4.7 none | Anthropic | 3.0 | 8.9 | 0/1 | 1.46s |
| #10 | Claude Opus 4.8 medium | Anthropic | 3.0 | 8.7 | 0/1 | 6.14s |
| #11 | Claude Opus 4.7 medium | Anthropic | 3.0 | 8.7 | 0/1 | 2.25s |
| #14 | Qwen3.6 Max Preview medium | Qwen | 3.0 | 8.5 | 0/1 | 60.6s |
| #17 | GLM 5 medium | Z.ai | 3.0 | 8.3 | 0/1 | 67.4s |
| #18 | Qwen3.7 Plus medium | Qwen | 3.0 | 8.2 | 0/1 | 91.1s |
| #19 | Seed-2.0-Lite medium | Bytedance Seed | 3.0 | 8.2 | 0/1 | 48.3s |