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: 测试正确 ↓.
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） |
|---|---|---|---|---|---|---|---|
| #68 | GLM 5.2 high | Z.ai | 10.0 | 8.0 | $1.188 | 2/2 | 321.5s |
| #74 | Qwen3.8 27B low | Qwen | 10.0 | 7.9 | ~$0.071 | 2/2 | 90.6s |
| #76 | Qwen3.6 Plus medium | Qwen | 10.0 | 7.8 | $0.418 | 2/2 | 163.3s |
| #78 | GLM 5.2 medium | Z.ai | 5.0 | 7.8 | $0.224 | 1/1 | 52.0s |
| #79 | GPT-5.6 Terra medium | OpenAI | 10.0 | 7.8 | $0.523 | 2/2 | 11.1s |
| #80 | Claude Sonnet 4.6 medium | Anthropic | 10.0 | 7.8 | $2.126 | 2/2 | 93.7s |
| #83 | Claude Opus 4.8 low | Anthropic | 9.9 | 7.8 | $2.089 | 2/2 | 36.9s |
| #85 | GLM 5 medium | Z.ai | 5.0 | 7.7 | $0.228 | 1/1 | 29.0s |
| #87 | Claude Opus 4.6 medium | Anthropic | 10.0 | 7.7 | $2.961 | 2/2 | 114.1s |
| #88 | DeepSeek V4 Pro high | DeepSeek | 10.0 | 7.7 | $0.476 | 2/2 | 79.0s |
| #90 | GLM 5 Turbo medium | Z.ai | 5.0 | 7.6 | $0.323 | 1/1 | 13.9s |
| #91 | GPT-5.6 Luna high | OpenAI | 10.0 | 7.6 | $0.179 | 2/2 | 19.0s |
| #92 | Solar Pro 4 xhigh | Upstage | 10.0 | 7.6 | $0.050 | 2/2 | 202.5s |
| #95 | GPT-5.4 Nano medium | OpenAI | 9.9 | 7.5 | $0.142 | 2/2 | 32.2s |
| #97 | MiniMax M3 medium | Minimax | 10.0 | 7.5 | $0.300 | 2/2 | 138.2s |