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） |
|---|---|---|---|---|---|---|---|
| #61 | Muse Spark 1.2 medium | Meta | 0.6 | 0.9 | $1.590 | 0/1 | 10.7s |
| #64 | Pareto 26.9 default | Unbiased | 0.6 | 0.9 | $1.864 | 0/1 | 6.55s |
| #66 | Qwen3.8 MAX low | Qwen | 0.6 | 0.9 | $1.089 | 0/1 | 5.29s |
| #67 | GPT-5.4 medium | OpenAI | 0.5 | 0.9 | $2.213 | 0/1 | 4.92s |
| #72 | Muse Spark 1.2 low | Meta | 0.5 | 0.9 | $0.881 | 0/1 | 8.46s |
| #73 | GPT-5.2 medium | OpenAI | 0.4 | 0.9 | $1.558 | 0/1 | 4.32s |
| #74 | Qwen3.8 27B high | Qwen | 0.5 | 0.9 | ~$0.298 | 0/1 | 8.45s |
| #76 | Seed 2.1 Turbo medium | Bytedance Seed | 0.6 | 0.9 | $2.042 | 0/1 | 40.6s |
| #81 | Claude Sonnet 5.5 xhigh | Anthropic | 0.6 | 0.9 | $1.516 | 0/1 | 9.10s |
| #82 | Claude Sonnet 5.5 high | Anthropic | 0.6 | 0.9 | $1.175 | 0/1 | 6.93s |
| #83 | Claude Haiku 5.5 low | Anthropic | 0.5 | 0.9 | $0.061 | 0/1 | 1.38s |
| #84 | Qwen3.8 Max (0902) low | Qwen | 0.6 | 0.9 | $1.131 | 0/1 | 8.91s |
| #87 | Claude Sonnet 5 medium | Anthropic | 0.5 | 0.9 | $1.438 | 0/1 | 4.32s |
| #90 | Nemotron 3.5 Super VL high | NVIDIA | 0.6 | 0.8 | $0.349 | 0/1 | 14.3s |
| #91 | Qwen3.8 2.4T A95B low | Qwen | 0.6 | 0.8 | $4.016 | 0/1 | 23.0s |