通用智能 排名
看看哪些 AI 模型在 通用智能 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 ↑.
461/461
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 | 通用智能 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #294 | MiMo-V2.6-Pro none | Xiaomi | 0.5 | 0.6 | $0.193 | 0/1 | 1.40s |
| #295 | Inkling Small medium | Thinkingmachines | 0.5 | 0.6 | $0.113 | 0/1 | 2.58s |
| #297 | Gemini 3.1 Flash Lite minimal | 0.4 | 0.6 | $0.080 | 0/1 | 791ms | |
| #298 | gpt-oss-120b medium | OpenAI | 0.4 | 0.6 | $0.030 | 0/1 | 7.90s |
| #299 | Gemini 3.1 Flash Lite none | 0.4 | 0.6 | $0.069 | 0/1 | 992ms | |
| #301 | Claude Sonnet 5 none | Anthropic | 0.5 | 0.6 | $1.095 | 0/1 | 2.81s |
| #302 | Nemotron 3 Ultra none | NVIDIA | 0.5 | 0.6 | $0.164 | 0/1 | 13.5s |
| #304 | Qwen3.8 Flash Next none | Qwen | 0.6 | 0.6 | ~$0.011 | 0/1 | 1.09s |
| #305 | DeepSeek V4.1 Flash 1017 none | DeepSeek | 0.5 | 0.6 | $0.055 | 0/1 | 616ms |
| #306 | GPT-5.6 Terra none | OpenAI | 0.5 | 0.6 | $0.377 | 0/1 | 1.03s |
| #307 | DeepSeek V4.1 Flash none | DeepSeek | 0.6 | 0.6 | $0.391 | 0/1 | 1.69s |
| #308 | Ling 3.0 Flash high | Inclusionai | 0.5 | 0.6 | $0.021 | 0/1 | 2.98s |
| #309 | Ring 2.6 1t medium | Inclusionai | 0.4 | 0.6 | $0.102 | 0/1 | 58.3s |
| #310 | Trinity Large Thinking high | Arcee AI | 0.6 | 0.6 | $0.794 | 0/1 | 12.9s |
| #311 | GPT-5 Nano medium | OpenAI | 0.4 | 0.6 | $0.159 | 0/1 | 17.5s |