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 ↓.
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） |
|---|---|---|---|---|---|---|---|
| #43 | Muse Spark 1.3 medium | Meta | 3.0 | 8.8 | $1.469 | 0/1 | 85.6s |
| #44 | Gemini 3.5 Flash Lite high | 3.0 | 8.8 | $0.540 | 0/1 | 9.68s | |
| #45 | Claude Opus 4.8 medium | Anthropic | 3.0 | 8.8 | $1.983 | 0/1 | 6.14s |
| #46 | Claude Opus 5 low | Anthropic | 3.0 | 8.7 | $1.121 | 0/1 | 6.48s |
| #48 | GLM 5.3 Flash max | Z.ai | 3.0 | 8.7 | $0.117 | 0/1 | 46.8s |
| #49 | Claude Opus 4.7 medium | Anthropic | 3.0 | 8.7 | $1.476 | 0/1 | 2.25s |
| #50 | Muse Spark 1.2 high | Meta | 3.0 | 8.7 | $1.771 | 0/1 | 15.0s |
| #51 | Muse Spark 1.2 medium | Meta | 3.0 | 8.6 | $1.339 | 0/1 | 12.8s |
| #52 | Muse Spark 1.1 medium | Meta | 3.0 | 8.6 | $1.420 | 0/1 | 18.5s |
| #53 | Claude Fable 5 medium | Anthropic | 3.0 | 8.6 | $3.004 | 0/1 | 25.6s |
| #54 | Qwen3.6 Max Preview medium | Qwen | 3.0 | 8.6 | $1.132 | 0/1 | 60.6s |
| #55 | Qwen3.8 Max low | Qwen | 3.0 | 8.6 | $0.702 | 0/1 | 12.4s |
| #56 | GPT-5.4 medium | OpenAI | 3.0 | 8.5 | $1.560 | 0/1 | 14.0s |
| #57 | DeepSeek V4.1 Flash low | DeepSeek | 3.0 | 8.5 | $0.161 | 0/1 | 46.9s |
| #58 | DeepSeek V4.1 Flash high | DeepSeek | 3.0 | 8.5 | $0.205 | 0/1 | 38.0s |