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: 总成本 ↓.
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） |
|---|---|---|---|---|---|---|---|
| #373 | Mimo V2 Omni medium | Xiaomi | 0.5 | 0.5 | $0.683 | 0/1 | 3.61s |
| #173 | Gemini 2.5 Flash medium | 0.5 | 0.7 | $0.680 | 0/1 | 4.86s | |
| #120 | Nemotron 3 Ultra medium | NVIDIA | 0.4 | 0.8 | $0.674 | 0/1 | 2.52s |
| #283 | Beam 1.0 501B A23B high | Reflection | 0.5 | 0.6 | $0.674 | 0/1 | 1.94s |
| #55 | Gemini 4 Argon medium | 1.0 | 0.9 | $0.674 | 1/1 | 2.40s | |
| #277 | KAT-Coder-Pro V2.5 medium | Kwaipilot | 0.5 | 0.6 | $0.669 | 0/1 | 2.35s |
| #292 | Claude Sonnet 4.6 none | Anthropic | 0.6 | 0.6 | $0.661 | 0/1 | 2.56s |
| #231 | LongCat 2.0 low | Meituan | 0.3 | 0.7 | $0.630 | 0/1 | 22.5s |
| #54 | Gemini 3.5 Flash Lite high | 1.0 | 0.9 | $0.624 | 1/1 | 3.10s | |
| #126 | GLM 5.3 FlashX max | Z.ai | 1.0 | 0.8 | $0.623 | 1/1 | 5.01s |
| #69 | DeepSeek V4.1 Flash high | DeepSeek | 1.0 | 0.9 | $0.617 | 1/1 | 4.16s |
| #59 | Muse Spark Open low | Meta | 0.6 | 0.9 | $0.600 | 0/1 | 5.85s |
| #193 | GPT-5.2 Chat default | OpenAI | 0.4 | 0.7 | $0.594 | 0/1 | 3.20s |
| #70 | DeepSeek V4.1 Flash medium | DeepSeek | 1.0 | 0.9 | $0.591 | 1/1 | 3.13s |
| #135 | DeepSeek V4.1 Flash 1017 high | DeepSeek | 1.0 | 0.8 | $0.589 | 1/1 | 2.02s |