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: 响应时间（平均） ↓.
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） |
|---|---|---|---|---|---|---|---|
| #53 | Muse Spark 1.2 low | Meta | 10.0 | 8.7 | $0.881 | 1/1 | 56.8s |
| #46 | Muse Spark 1.2 medium | Meta | 10.0 | 8.9 | $1.590 | 1/1 | 56.7s |
| #8 | GPT-6 Astra xhigh | OpenAI | 10.0 | 9.9 | $6.213 | 1/1 | 56.7s |
| #71 | Gemini 3.1 Pro Preview medium | 4.7 | 8.4 | $1.585 | 0/1 | 56.2s | |
| #123 | Qwen3.6 Flash medium | Qwen | 10.0 | 7.4 | $0.858 | 1/1 | 56.1s |
| #90 | DeepSeek V4.1 Flash low | DeepSeek | 6.1 | 8.0 | $0.153 | 0/1 | 56.0s |
| #201 | Qwen3.5-122B-A10B none | Qwen | 10.0 | 6.4 | $0.308 | 1/1 | 55.9s |
| #250 | DeepSeek V4.1 Flash none | DeepSeek | 7.4 | 5.8 | $0.123 | 0/1 | 55.8s |
| #65 | Muse Spark 1.3 low | Meta | 10.0 | 8.5 | $0.911 | 1/1 | 55.1s |
| #61 | Claude Sonnet 5.5 xhigh | Anthropic | 10.0 | 8.6 | $1.516 | 1/1 | 54.9s |
| #155 | Gemini 3.1 Flash Lite Preview medium | 5.0 | 7.0 | $0.158 | 0/1 | 54.9s | |
| #84 | GPT-5.6 Terra medium | OpenAI | 10.0 | 8.2 | $0.744 | 1/1 | 54.7s |
| #12 | GPT-6.1 Sol high | OpenAI | 10.0 | 9.6 | $0.755 | 1/1 | 54.6s |
| #95 | GPT-5.6 Terra low | OpenAI | 10.0 | 7.9 | $0.645 | 1/1 | 54.6s |
| #291 | Mistral Small 4 medium | Mistral | 5.0 | 5.1 | $0.126 | 0/1 | 54.1s |