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） |
|---|---|---|---|---|---|---|---|
| #101 | Qwen3.8 27B medium | Qwen | 3.0 | 7.8 | ~$0.058 | 0/1 | 11.3s |
| #102 | Seed-2.0-Lite medium | Bytedance Seed | 3.0 | 7.8 | $0.236 | 0/1 | 48.3s |
| #103 | Claude Opus 4.8 low | Anthropic | 3.0 | 7.8 | $2.089 | 0/1 | 5.48s |
| #104 | Qwen3.7 Flash high | Qwen | 3.0 | 7.8 | $0.052 | 0/1 | 17.7s |
| #105 | GLM 5 medium | Z.ai | 3.0 | 7.7 | $0.228 | 0/1 | 67.4s |
| #106 | Seed-2.0-Code low | Bytedance Seed | 3.0 | 7.7 | $0.767 | 0/1 | 10.0s |
| #107 | Claude Opus 4.6 medium | Anthropic | 3.0 | 7.7 | $2.961 | 0/1 | 63.2s |
| #108 | DeepSeek V4 Pro high | DeepSeek | 3.0 | 7.7 | $0.447 | 0/1 | 34.0s |
| #109 | DeepSeek V4 Flash 0423 high | DeepSeek | 3.0 | 7.6 | $0.042 | 0/1 | 54.5s |
| #110 | MiMo-V2.6-Flash low | Xiaomi | 3.0 | 7.6 | $0.174 | 0/1 | 154.4s |
| #111 | GLM 5 Turbo medium | Z.ai | 3.0 | 7.6 | $0.323 | 0/1 | 40.2s |
| #112 | GPT-5.6 Luna high | OpenAI | 3.0 | 7.6 | $0.179 | 0/1 | 17.0s |
| #113 | Solar Pro 4 xhigh | Upstage | 3.0 | 7.6 | $0.150 | 0/1 | 119.9s |
| #114 | Nemotron 3 Ultra medium | NVIDIA | 3.0 | 7.6 | $0.567 | 0/1 | 38.5s |
| #115 | Claude Opus 5 none | Anthropic | 3.0 | 7.5 | $1.550 | 0/1 | 4.08s |