综合 排名
看看哪些 AI 模型在 综合 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 ↓.
316/316
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 | 综合 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #59 | Muse Spark 1.3 low | Meta | 7.3 | 8.2 | $0.689 | 1/2 | 25.7s |
| #107 | Kimi K2.7 Code medium | Moonshot AI | 7.3 | 7.4 | $0.687 | 1/2 | 66.0s |
| #209 | Mimo V2 Omni medium | Xiaomi | 5.0 | 5.9 | $0.683 | 1/1 | 25.9s |
| #188 | Qwen3.5-35B-A3B medium | Qwen | 3.8 | 6.1 | $0.675 | 0/2 | 512.8s |
| #56 | Muse Spark 1.1 low | Meta | 6.6 | 8.3 | $0.673 | 1/2 | 29.4s |
| #167 | Qwen3.6 35B A3B medium | Qwen | 3.0 | 6.6 | $0.672 | 0/2 | 817.6s |
| #26 | Gemini 3.5 Flash medium | 10.0 | 9.0 | $0.665 | 2/2 | 44.4s | |
| #113 | Claude Sonnet 4.6 none | Anthropic | 9.8 | 7.3 | $0.661 | 2/2 | 37.5s |
| #49 | Muse Spark 1.2 low | Meta | 9.8 | 8.4 | $0.655 | 2/2 | 17.0s |
| #22 | Gemini 3.8 Flash medium | 8.7 | 9.1 | $0.653 | 1/2 | 60.3s | |
| #164 | Gemini 3.1 Flash Lite Preview low | 3.0 | 6.6 | $0.646 | 0/2 | 160.6s | |
| #6 | Gemini 3.7 Flash high | 10.0 | 9.8 | $0.646 | 2/2 | 57.2s | |
| #58 | Gemini 2.5 Flash medium | 10.0 | 8.2 | $0.644 | 2/2 | 84.5s | |
| #199 | Trinity Large Thinking low | Arcee AI | 5.2 | 6.0 | $0.625 | 0/2 | 291.0s |
| #166 | Gemini 3.1 Flash Lite low | 3.2 | 6.6 | $0.621 | 0/2 | 161.2s |