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） |
|---|---|---|---|---|---|---|---|
| #155 | Trinity Large Thinking low | Arcee AI | 3.0 | 6.0 | $0.656 | 0/1 | 2.10s |
| #30 | Muse Spark 1.2 low | Meta | 3.0 | 8.4 | $0.650 | 0/1 | 10.00s |
| #37 | Muse Spark 1.1 low | Meta | 3.0 | 8.3 | $0.647 | 0/1 | 8.17s |
| #127 | Gemini 3.1 Flash Lite Preview low | 3.0 | 6.5 | $0.646 | 0/1 | 1.35s | |
| #38 | Gemini 2.5 Flash medium | 3.0 | 8.2 | $0.643 | 0/1 | 2.76s | |
| #13 | Gemini 3.5 Flash medium | 10.0 | 9.1 | $0.642 | 1/1 | 2.75s | |
| #215 | Trinity Large Thinking high | Arcee AI | 3.0 | 4.8 | $0.632 | 0/1 | 125.1s |
| #128 | Gemini 3.1 Flash Lite low | 3.0 | 6.5 | $0.621 | 0/1 | 1.46s | |
| #44 | GPT-5.2 Chat none | OpenAI | 3.0 | 8.0 | $0.604 | 0/1 | 6.89s |
| #97 | Kimi K2.5 medium | Moonshot AI | 3.0 | 7.0 | $0.600 | 0/1 | 83.9s |
| #72 | GPT-5.3 Chat none | OpenAI | 3.0 | 7.5 | $0.571 | 0/1 | 4.38s |
| #136 | Claude Sonnet 5 none | Anthropic | 3.0 | 6.3 | $0.548 | 0/1 | 4.31s |
| #239 | Grok Build 0.1 none | X AI | 3.0 | 4.0 | $0.547 | 0/1 | 36.1s |
| #108 | GPT-5.5 none | OpenAI | 3.0 | 6.9 | $0.544 | 0/1 | 5.01s |
| #21 | Gemini 3.5 Flash Lite high | 3.0 | 8.8 | $0.538 | 0/1 | 9.68s |