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: 响应时间（平均） ↓.
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） |
|---|---|---|---|---|---|---|---|
| #337 | Granite 4.2 8B none | IBM Granite | 3.0 | 4.3 | $0.037 | 0/1 | 14.6s |
| #37 | GPT-5.3-Codex medium | OpenAI | 2.8 | 8.9 | $0.988 | 0/1 | 14.4s |
| #196 | Inkling Small medium | Thinkingmachines | 3.0 | 6.6 | $0.113 | 0/1 | 14.2s |
| #24 | Claude Opus 5 high | Anthropic | 3.0 | 9.2 | $3.070 | 0/1 | 14.1s |
| #6 | GPT-6 Astra xhigh | OpenAI | 10.0 | 9.9 | $5.156 | 1/1 | 14.1s |
| #63 | Grok 4.5 low | X AI | 3.0 | 8.4 | $0.945 | 0/1 | 14.0s |
| #56 | GPT-5.4 medium | OpenAI | 3.0 | 8.5 | $1.560 | 0/1 | 14.0s |
| #27 | Qwen3.8 Max (0902) low | Qwen | 3.0 | 9.1 | $0.664 | 0/1 | 13.3s |
| #51 | Muse Spark 1.2 medium | Meta | 3.0 | 8.6 | $1.339 | 0/1 | 12.8s |
| #93 | Qwen3.8 27B low | Qwen | 3.0 | 7.9 | ~$0.071 | 0/1 | 12.6s |
| #182 | MiMo-V2.5-Pro medium | Xiaomi | 3.0 | 6.8 | $0.221 | 0/1 | 12.5s |
| #55 | Qwen3.8 Max low | Qwen | 3.0 | 8.6 | $0.702 | 0/1 | 12.4s |
| #140 | GLM 5.3 Flash high | Z.ai | 3.0 | 7.3 | $0.057 | 0/1 | 11.5s |
| #34 | Qwen3.8 Max medium | Qwen | 3.0 | 9.0 | $0.771 | 0/1 | 11.5s |
| #101 | Qwen3.8 27B medium | Qwen | 3.0 | 7.8 | ~$0.058 | 0/1 | 11.3s |