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: 指标 ↑.
319/319
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） |
|---|---|---|---|---|---|---|---|
| #291 | Qwen3 Coder Next medium | Qwen | 6.3 | 4.6 | $0.034 | 0/1 | 1.39s |
| #31 | Qwen3.8 Max (0902) high | Qwen | 6.5 | 8.9 | $2.736 | 0/1 | 75.1s |
| #34 | Seed 2.1 Turbo high | Bytedance Seed | 6.5 | 8.9 | $1.797 | 0/1 | 25.7s |
| #49 | Qwen3.8 Max low | Qwen | 6.5 | 8.6 | $0.702 | 0/1 | 5.29s |
| #51 | Grok 4.5 medium | X AI | 6.5 | 8.5 | $2.042 | 0/1 | 12.8s |
| #69 | DeepSeek V4 Flash 0731 low | DeepSeek | 6.5 | 8.0 | $0.072 | 0/1 | 7.63s |
| #89 | Seed-2.0-Code low | Bytedance Seed | 6.5 | 7.7 | $0.767 | 0/1 | 11.1s |
| #135 | GPT-5.6 Sol none | OpenAI | 6.5 | 7.0 | $0.201 | 0/1 | 1.52s |
| #142 | Kimi K2.5 medium | Moonshot AI | 6.5 | 7.0 | $0.479 | 0/1 | 69.7s |
| #173 | Qwen3.6 27B medium | Qwen | 6.5 | 6.5 | $0.577 | 0/1 | 39.5s |
| #209 | Qwen3.5-35B-A3B none | Qwen | 6.5 | 5.9 | $0.151 | 0/1 | 1.19s |
| #280 | Trinity Large Thinking high | Arcee AI | 6.5 | 4.8 | $0.592 | 0/1 | 12.9s |
| #85 | Seed-2.0-Lite medium | Bytedance Seed | 6.7 | 7.8 | $0.236 | 0/1 | 18.2s |
| #285 | Hunter Alpha medium | OpenRouter | 7.0 | 4.7 | $0.000 | 0/1 | 6.44s |
| #236 | Hy4 preview low | Tencent | 7.5 | 5.6 | $1.745 | 0/1 | 110.4s |