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: 总成本 ↓.
250/250
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） |
|---|---|---|---|---|---|---|---|
| #20 | Muse Spark 1.2 high | Meta | 3.0 | 8.8 | $1.632 | 0/1 | 15.0s |
| #69 | Claude Opus 5 none | Anthropic | 3.0 | 7.5 | $1.550 | 0/1 | 4.08s |
| #29 | GPT-5.4 medium | OpenAI | 3.0 | 8.5 | $1.533 | 0/1 | 14.0s |
| #11 | Claude Opus 5 medium | Anthropic | 3.0 | 9.2 | $1.486 | 0/1 | 7.03s |
| #23 | Claude Opus 4.7 medium | Anthropic | 3.0 | 8.7 | $1.477 | 0/1 | 2.25s |
| #9 | Gemini 3.1 Pro Preview medium | 10.0 | 9.2 | $1.361 | 1/1 | 6.27s | |
| #26 | Muse Spark 1.1 medium | Meta | 3.0 | 8.6 | $1.357 | 0/1 | 18.5s |
| #6 | GPT-5.6 Sol medium | OpenAI | 4.7 | 9.4 | $1.316 | 0/1 | 4.94s |
| #1 | Gemini 3.6 Flash high | 10.0 | 10.0 | $1.305 | 1/1 | 6.35s | |
| #8 | GPT-5.5 low | OpenAI | 3.0 | 9.3 | $1.253 | 0/1 | 10.1s |
| #7 | GPT-5.6 Sol high | OpenAI | 4.7 | 9.4 | $1.234 | 0/1 | 6.97s |
| #25 | Muse Spark 1.2 medium | Meta | 3.0 | 8.6 | $1.227 | 0/1 | 12.8s |
| #107 | Step 3.7 Flash high | Stepfun | 3.0 | 6.9 | $1.207 | 0/1 | 149.3s |
| #92 | Qwen3.5-122B-A10B medium | Qwen | 3.0 | 7.1 | $1.206 | 0/1 | 52.9s |
| #86 | Claude Opus 4.8 none | Anthropic | 3.0 | 7.3 | $1.166 | 0/1 | 3.41s |