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。 排序方式: 测试正确 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #21 | GLM 5 Turbo medium | Z.ai | 3.0 | 8.4 | $0.323 | 0/1 | 40.2s |
| #22 | GPT-5.2 medium | OpenAI | 3.0 | 8.4 | $0.548 | 0/1 | 28.2s |
| #23 | DeepSeek V4 Flash high | DeepSeek | 3.0 | 8.3 | $0.027 | 0/1 | 54.5s |
| #24 | Gemini 2.5 Flash medium | 3.0 | 8.2 | $0.379 | 0/1 | 2.76s | |
| #25 | Qwen3.7 Plus medium | Qwen | 3.0 | 8.2 | $0.177 | 0/1 | 91.1s |
| #26 | Nemotron 3 Ultra 550b A55b medium | NVIDIA | 3.0 | 8.1 | $0.158 | 0/1 | 38.5s |
| #27 | GPT-5.4 Mini medium | OpenAI | 3.0 | 8.0 | $0.526 | 0/1 | 30.1s |
| #28 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 3.0 | 8.0 | $0.310 | 0/1 | 103.8s |
| #29 | Qwen3.5-27B medium | Qwen | 3.0 | 7.9 | $0.536 | 0/1 | 85.1s |
| #30 | Qwen3.6 Plus medium | Qwen | 3.0 | 7.8 | $0.294 | 0/1 | 47.5s |
| #31 | Claude Sonnet 4.6 medium | Anthropic | 3.0 | 7.8 | $1.418 | 0/1 | 30.1s |
| #32 | Gemini 3.1 Flash Lite Preview medium | 3.0 | 7.8 | $0.068 | 0/1 | 2.68s | |
| #33 | Qwen3.5 Plus 2026-04-20 medium | Qwen | 3.0 | 7.8 | $0.317 | 0/1 | 92.6s |
| #34 | Gemini 3.1 Flash Lite medium | 3.0 | 7.8 | $0.071 | 0/1 | 3.08s | |
| #35 | Kimi K2.6 medium | Moonshot AI | 3.0 | 7.8 | $0.889 | 0/1 | 130.3s |