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） |
|---|---|---|---|---|---|---|---|
| #138 | Step 3.7 Flash medium | Stepfun | 0.4 | 0.8 | $0.571 | 0/1 | 6.85s |
| #139 | Grok 4.6 medium | X AI | 0.4 | 0.8 | $2.270 | 0/1 | 17.3s |
| #140 | Qwen3.7 Plus none | Qwen | 0.5 | 0.8 | $0.178 | 0/1 | 1.33s |
| #141 | Grok 4.5 low | X AI | 0.6 | 0.8 | $1.345 | 0/1 | 4.88s |
| #142 | DeepSeek V4 Flash 0731 medium | DeepSeek | 0.6 | 0.8 | $0.460 | 0/1 | 12.2s |
| #144 | GPT-6 Luna high | OpenAI | 0.5 | 0.8 | $0.074 | 0/1 | 17.4s |
| #145 | Muse Glimmer 30B high | Meta | 0.5 | 0.8 | $0.506 | 0/1 | 6.36s |
| #146 | Nemotron 3.5 Super VL medium | NVIDIA | 0.6 | 0.8 | $0.437 | 0/1 | 12.7s |
| #147 | Claude Haiku 5.5 medium | Anthropic | 0.4 | 0.8 | $0.063 | 0/1 | 5.17s |
| #148 | Qwen3.5 Plus 2026-04-20 medium | Qwen | 0.5 | 0.8 | $0.435 | 0/1 | 25.3s |
| #149 | Qwen3.7 Flash low | Qwen | 0.4 | 0.8 | $0.071 | 0/1 | 14.4s |
| #150 | Muse Glimmer 30B medium | Meta | 0.5 | 0.8 | $0.288 | 0/1 | 5.16s |
| #152 | Qwen3.8 Flash Next medium | Qwen | 0.5 | 0.8 | ~$0.047 | 0/1 | 7.29s |
| #153 | GPT-6 Luna low | OpenAI | 0.4 | 0.8 | $0.033 | 0/1 | 1.46s |
| #154 | Qwen3.8 27B low | Qwen | 0.5 | 0.8 | ~$0.089 | 0/1 | 5.37s |