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 ↓.
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） |
|---|---|---|---|---|---|---|---|
| #217 | GLM 5.3 FlashX low | Z.ai | 3.0 | 6.3 | $0.090 | 0/1 | 2.69s |
| #332 | Grok 4.20 Beta none | X AI | 0.0 | 4.4 | $0.087 | 0/0 | 0ms |
| #184 | Gemini 3 Flash Preview none | 3.0 | 6.8 | $0.085 | 0/1 | 1.07s | |
| #234 | Nemotron 3 Ultra none | NVIDIA | 3.0 | 6.1 | $0.084 | 0/1 | 1.83s |
| #185 | Gemma 4 26B A4B medium | 3.0 | 6.8 | $0.084 | 0/1 | 180.9s | |
| #307 | Laguna S 2.1 low | Poolside | 3.0 | 5.0 | $0.082 | 0/1 | 202.5s |
| #160 | DeepSeek V3.2 medium | DeepSeek | 3.0 | 7.0 | $0.078 | 0/1 | 84.0s |
| #262 | KAT-Coder-Air V2.5 high | Kwaipilot | 3.0 | 5.6 | $0.077 | 0/1 | 21.7s |
| #272 | Qwen3.6 27B none | Qwen | 3.0 | 5.5 | $0.075 | 0/1 | 4.03s |
| #241 | Qwen3.5-Flash none | Qwen | 3.0 | 6.0 | $0.073 | 0/1 | 588ms |
| #200 | Qwen3.5 Plus 2026-02-15 none | Qwen | 3.0 | 6.6 | $0.073 | 0/1 | 1.11s |
| #131 | GPT-5.6 Luna medium | OpenAI | 3.0 | 7.4 | $0.072 | 0/1 | 6.64s |
| #93 | Qwen3.8 27B low | Qwen | 3.0 | 7.9 | ~$0.071 | 0/1 | 12.6s |
| #225 | gpt-oss-120b medium | OpenAI | 3.0 | 6.1 | $0.070 | 0/1 | 26.5s |
| #320 | KAT-Coder-Air V2.5 none | Kwaipilot | 3.0 | 4.8 | $0.070 | 0/1 | 18.0s |