常识问答：答案错误
常识问答
答案错误
看看哪些 AI 模型在 常识问答 上最容易遇到 答案错误，更快找出薄弱点。
323/323
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 | 答案错误 次数 | 分类得分 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #59 | Muse Spark Open low | Meta | 1 | 0.3 | $0.600 | 0/1 | 14.2s |
| #60 | Muse Spark 1.2 high | Meta | 1 | 0.3 | $2.018 | 0/1 | 15.0s |
| #61 | Muse Spark 1.2 medium | Meta | 1 | 0.3 | $1.590 | 0/1 | 12.8s |
| #62 | Muse Spark 1.1 medium | Meta | 1 | 0.3 | $1.665 | 0/1 | 18.5s |
| #64 | Pareto 26.9 default | Unbiased | 1 | 0.3 | $1.864 | 0/1 | 28.6s |
| #65 | Kimi K3.1 Pro low | Moonshot AI | 1 | 0.3 | $1.836 | 0/1 | 44.6s |
| #66 | Qwen3.8 MAX low | Qwen | 1 | 0.3 | $1.089 | 0/1 | 12.4s |
| #67 | GPT-5.4 medium | OpenAI | 1 | 0.3 | $2.213 | 0/1 | 14.0s |
| #69 | DeepSeek V4.1 Flash high | DeepSeek | 1 | 0.3 | $0.617 | 0/1 | 38.0s |
| #70 | DeepSeek V4.1 Flash medium | DeepSeek | 1 | 0.3 | $0.591 | 0/1 | 20.3s |
| #72 | Muse Spark 1.2 low | Meta | 1 | 0.3 | $0.881 | 0/1 | 10.00s |
| #73 | GPT-5.2 medium | OpenAI | 1 | 0.3 | $1.558 | 0/1 | 28.2s |
| #74 | Qwen3.8 27B high | Qwen | 1 | 0.3 | ~$0.298 | 0/1 | 264.0s |
| #76 | Seed 2.1 Turbo medium | Bytedance Seed | 1 | 0.3 | $2.042 | 0/1 | 91.0s |
| #77 | GPT-6 Sol low | OpenAI | 1 | 0.5 | $0.477 | 0/1 | 3.67s |