AI news
公司内部站点 · 页面资源保存在本地(2026-10-17 17:18 UTC)· 独立 X 采集尚未配置;互动计数仅限本站

Qwen introduces RecreationBench for hybrid computer-use agents

ModelScope

ModelScope said Qwen has introduced RecreationBench, a benchmark for Hybrid Computer-Use Agents with 250 application-recreation tasks across Ubuntu, macOS, Windows, Android, and Web. The tasks span domains such as productivity, development, graphics, multimedia, and science.

Unlike GUI-only or terminal-only benchmarks, agents must explore a running reference app, recreate it in code, and pass both programmatic tests and VLM-based visual evaluation. The dataset is available at https://modelscope.ai/datasets/Qwen/RecreationBench.