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: 总成本 ↓.
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） |
|---|---|---|---|---|---|---|---|
| #124 | Kimi K2.6 medium | Moonshot AI | 10.0 | 7.2 | $1.247 | 1/1 | 17.8s |
| #149 | Step 3.7 Flash high | Stepfun | 5.5 | 6.8 | $1.229 | 0/1 | 4.17s |
| #130 | Qwen3.5-122B-A10B medium | Qwen | 3.4 | 7.1 | $1.207 | 0/1 | 34.1s |
| #71 | GLM 5.2 high | Z.ai | 10.0 | 8.0 | $1.188 | 1/1 | 12.9s |
| #55 | GPT-5.2 medium | OpenAI | 3.7 | 8.4 | $1.182 | 0/1 | 4.32s |
| #123 | Claude Opus 4.8 none | Anthropic | 10.0 | 7.3 | $1.166 | 1/1 | 3.48s |
| #25 | Qwen3.7 Max medium | Qwen | 10.0 | 9.1 | $1.157 | 1/1 | 11.7s |
| #150 | Seed-2.0-Code medium | Bytedance Seed | 4.8 | 6.8 | $1.153 | 0/1 | 11.4s |
| #191 | Qwen3.5-35B-A3B medium | Qwen | 2.8 | 6.1 | $1.148 | 0/1 | 30.3s |
| #48 | Qwen3.6 Max Preview medium | Qwen | 10.0 | 8.6 | $1.132 | 1/1 | 32.2s |
| #106 | Grok Build 0.1 medium | X AI | 4.4 | 7.5 | $1.130 | 0/1 | 18.4s |
| #40 | Claude Opus 5 low | Anthropic | 10.0 | 8.7 | $1.121 | 1/1 | 3.76s |
| #147 | Gemini 3.5 Flash none | 10.0 | 6.9 | $1.093 | 1/1 | 3.46s | |
| #67 | Inkling high | Thinkingmachines | 10.0 | 8.0 | $1.046 | 1/1 | 6.53s |
| #32 | GPT-5.3-Codex medium | OpenAI | 4.6 | 8.9 | $0.988 | 0/1 | 4.87s |