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: 指标 ↑.
364/364
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） |
|---|---|---|---|---|---|---|---|
| #225 | gpt-oss-120b medium | OpenAI | 3.0 | 6.1 | $0.070 | 0/1 | 26.5s |
| #226 | Qwen3.7 Flash none | Qwen | 3.0 | 6.1 | $0.019 | 0/1 | 766ms |
| #227 | Gemini 3.1 Flash Lite none | 3.0 | 6.1 | $0.046 | 0/1 | 733ms | |
| #228 | Qwen3.5-Flash medium | Qwen | 3.0 | 6.1 | $0.142 | 0/1 | 49.0s |
| #229 | Inkling low | Thinkingmachines | 3.0 | 6.1 | $0.187 | 0/1 | 3.12s |
| #230 | Trinity Large Thinking medium | Arcee AI | 3.0 | 6.1 | $0.756 | 0/1 | 97.4s |
| #231 | Qwen3.6 Flash none | Qwen | 3.0 | 6.1 | $0.062 | 0/1 | 649ms |
| #232 | Gemma 4 31B none | 3.0 | 6.1 | $0.016 | 0/1 | 1.25s | |
| #233 | Qwen3.5 Plus 2026-04-20 none | Qwen | 3.0 | 6.1 | $0.122 | 0/1 | 33.3s |
| #234 | Nemotron 3 Ultra none | NVIDIA | 3.0 | 6.1 | $0.084 | 0/1 | 1.83s |
| #235 | Trinity Large Thinking low | Arcee AI | 3.0 | 6.0 | $0.625 | 0/1 | 2.10s |
| #236 | Gemini 2.5 Flash none | 3.0 | 6.0 | $0.017 | 0/1 | 1.15s | |
| #238 | GPT-5.6 Terra none | OpenAI | 3.0 | 6.0 | $0.280 | 0/1 | 787ms |
| #239 | Gemini 3 PRO Preview medium | 3.0 | 6.0 | $0.385 | 0/1 | 0ms | |
| #240 | GPT-5 Nano medium | OpenAI | 3.0 | 6.0 | $0.118 | 0/1 | 20.1s |