智能体任务 排名
看看哪些 AI 模型在 智能体任务 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 ↑.
380/380
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 | 智能体任务 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #3 | GPT-6 Sol high | OpenAI | 10.0 | 9.9 | $0.921 | 1/1 | 53.3s |
| #32 | Qwen3.8 MAX medium | Qwen | 10.0 | 9.2 | $0.948 | 1/1 | 115.3s |
| #10 | Gemini 3.6 Flash medium | 10.0 | 9.8 | $0.970 | 1/1 | 61.8s | |
| #199 | Grok 4.3 medium | X AI | 3.9 | 6.5 | $0.989 | 0/1 | 51.6s |
| #4 | GPT-6.1 Sol max | OpenAI | 10.0 | 9.9 | $1.006 | 1/1 | 80.2s |
| #148 | Qwen3.6 27B medium | Qwen | 10.0 | 7.2 | $1.006 | 1/1 | 145.9s |
| #99 | GPT-5.4 Mini medium | OpenAI | 10.0 | 7.9 | $1.008 | 1/1 | 100.7s |
| #119 | GLM 5.1 medium | Z.ai | 10.0 | 7.5 | $1.066 | 1/1 | 225.6s |
| #246 | Claude Sonnet 5 none | Anthropic | 4.7 | 5.9 | $1.095 | 0/1 | 64.7s |
| #39 | Qwen3.8 Max (0902) medium | Qwen | 10.0 | 9.0 | $1.096 | 1/1 | 127.5s |
| #192 | Claude Sonnet 5.5 medium | Anthropic | 10.0 | 6.5 | $1.100 | 1/1 | 51.2s |
| #76 | GPT-5.6 Terra high | OpenAI | 10.0 | 8.3 | $1.116 | 1/1 | 66.4s |
| #63 | Qwen3.8 Max (0902) low | Qwen | 6.1 | 8.6 | $1.131 | 0/1 | 136.0s |
| #154 | Qwen3.6 Max Preview medium | Qwen | 0.0 | 7.0 | $1.132 | 0/0 | 0ms |
| #96 | Qwen3.5-27B medium | Qwen | 10.0 | 7.9 | $1.135 | 1/1 | 146.5s |