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 ↑.
250/250
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） |
|---|---|---|---|---|---|---|---|
| #55 | GPT-5.6 Terra medium | OpenAI | 3.0 | 7.8 | $0.271 | 0/1 | 10.1s |
| #56 | Claude Sonnet 4.6 medium | Anthropic | 3.0 | 7.8 | $2.057 | 0/1 | 30.1s |
| #57 | Qwen3.7 Flash high | Qwen | 3.0 | 7.8 | $0.051 | 0/1 | 17.7s |
| #58 | Claude Opus 4.8 low | Anthropic | 3.0 | 7.8 | $2.077 | 0/1 | 5.48s |
| #59 | GLM 5 medium | Z.ai | 3.0 | 7.7 | $0.307 | 0/1 | 67.4s |
| #60 | Claude Opus 4.6 medium | Anthropic | 3.0 | 7.7 | $3.059 | 0/1 | 63.2s |
| #61 | GPT-5.6 Luna high | OpenAI | 3.0 | 7.7 | $0.102 | 0/1 | 17.0s |
| #62 | DeepSeek V4 Flash high | DeepSeek | 3.0 | 7.7 | $0.060 | 0/1 | 54.5s |
| #63 | DeepSeek V4 Pro high | DeepSeek | 3.0 | 7.7 | $0.200 | 0/1 | 34.0s |
| #64 | MiniMax M3 medium | Minimax | 3.0 | 7.6 | $0.286 | 0/1 | 100.8s |
| #65 | Grok Build 0.1 medium | X AI | 3.0 | 7.6 | $1.097 | 0/1 | 53.5s |
| #66 | GLM 5 Turbo medium | Z.ai | 3.0 | 7.6 | $0.323 | 0/1 | 40.2s |
| #67 | GPT-5.6 Luna medium | OpenAI | 3.0 | 7.6 | $0.036 | 0/1 | 6.64s |
| #68 | Nemotron 3 Ultra medium | NVIDIA | 3.0 | 7.5 | $0.774 | 0/1 | 38.5s |
| #69 | Claude Opus 5 none | Anthropic | 3.0 | 7.5 | $1.550 | 0/1 | 4.08s |