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 ↑.
216/216
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） |
|---|---|---|---|---|---|---|---|
| #24 | GPT-5.2 medium | OpenAI | 10.0 | 8.4 | $0.951 | 2/2 | 58.5s |
| #5 | GPT-5.6 Sol low | OpenAI | 10.0 | 9.5 | $0.971 | 2/2 | 14.6s |
| #32 | Inkling high | Thinkingmachines | 7.3 | 8.0 | $1.006 | 1/2 | 63.8s |
| #48 | GPT-5.6 Luna high | OpenAI | 10.0 | 7.7 | $1.017 | 2/2 | 19.0s |
| #72 | Kimi K2.6 medium | Moonshot AI | 6.9 | 7.2 | $1.036 | 1/2 | 458.6s |
| #76 | Qwen3.5-122B-A10B medium | Qwen | 6.4 | 7.1 | $1.046 | 1/2 | 313.5s |
| #38 | GPT-5.6 Terra high | OpenAI | 8.7 | 8.0 | $1.055 | 1/2 | 13.7s |
| #83 | Gemini 3.5 Flash none | 3.0 | 7.0 | $1.079 | 0/2 | 0ms | |
| #52 | Grok Build 0.1 medium | X AI | 10.0 | 7.6 | $1.097 | 2/2 | 65.1s |
| #11 | Qwen3.7 Max medium | Qwen | 8.7 | 9.2 | $1.116 | 1/2 | 287.8s |
| #22 | Qwen3.6 Max Preview medium | Qwen | 7.3 | 8.4 | $1.143 | 1/2 | 177.5s |
| #70 | Claude Opus 4.8 none | Anthropic | 9.8 | 7.3 | $1.166 | 2/2 | 26.4s |
| #90 | Step 3.7 Flash high | Stepfun | 8.7 | 6.9 | $1.207 | 1/2 | 41.2s |
| #8 | GPT-5.6 Sol high | OpenAI | 10.0 | 9.4 | $1.234 | 2/2 | 25.0s |
| #9 | GPT-5.5 low | OpenAI | 10.0 | 9.3 | $1.253 | 2/2 | 13.7s |