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 ↓.
455/455
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） |
|---|---|---|---|---|---|---|---|
| #139 | Muse Glimmer 30B high | Meta | 0.6 | 0.8 | $0.506 | 1/2 | 115.4s |
| #326 | Claude Opus 4.7 none | Anthropic | 0.5 | 0.5 | $0.505 | 1/1 | 18.3s |
| #228 | Beam 1.0 501B A23B medium | Reflection | 0.3 | 0.7 | $0.499 | 0/2 | 2.62s |
| #131 | GLM 5.3 high | Z.ai | 0.6 | 0.8 | $0.495 | 1/2 | 64.0s |
| #112 | DeepSeek V4.1 Flash low | DeepSeek | 1.0 | 0.8 | $0.494 | 2/2 | 24.7s |
| #319 | Kimi K2.6 none | Moonshot AI | 0.3 | 0.5 | $0.486 | 0/2 | 77.8s |
| #105 | GPT-5.6 Terra medium | OpenAI | 1.0 | 0.8 | $0.483 | 2/2 | 11.1s |
| #178 | GLM 5 medium | Z.ai | 0.5 | 0.7 | $0.479 | 1/1 | 29.0s |
| #72 | GPT-6 Sol low | OpenAI | 1.0 | 0.9 | $0.477 | 2/2 | 8.13s |
| #136 | DeepSeek V4 Flash 0731 medium | DeepSeek | 0.7 | 0.8 | $0.460 | 1/2 | 150.6s |
| #16 | GPT-6.1 Sol low | OpenAI | 1.0 | 1.0 | $0.460 | 2/2 | 10.9s |
| #324 | GLM 5V Turbo medium | Z.ai | 0.3 | 0.5 | $0.457 | 0/1 | 15.1s |
| #237 | GLM 5.1 none | Z.ai | 0.3 | 0.6 | $0.451 | 0/2 | 46.9s |
| #123 | Qwen3.7 Max none | Qwen | 0.7 | 0.8 | $0.451 | 1/2 | 37.2s |
| #179 | Step 3.7 Flash low | Stepfun | 0.7 | 0.7 | $0.449 | 1/2 | 66.2s |