Quality assessment is a critical component in crowdsourcing-based software engineering(CBSE)as soft-ware products are developed by the crowd with unknown or varied skills and motivations.In this paper,we propose a novel metric called the project score to measure the perfor-mance of projects and the quality of products for competition-based software crowdsourcing development(CBSCD)activ-ities.To the best of our knowledge,this is the first work to deal with the quality issue of CBSE in the perspective of projects instead of contests.In particular,we develop a hi-erarchical quality evaluation framework for CBSCD projects and come up with two metric aggregation models for project scores.The first model is a modified squale model that can locate the software modules of poor quality,and the second one is a clustering-based aggregation model,which takes dif-ferent impacts of phases into account.To test the effective-ness of the proposed metrics,we conduct an empirical study on TopCoder,which is a famous CBSCD platform.Results show that the proposed project score is a strong indicator of the performance and product quality of CBSCD projects.We also find that the clustering-based aggregation model outper-forms the Squale one by increasing the percentage of the per-formance evaluation criterion of aggregation models by an additional 29％.Our approach to quality assessment for CB-SCD projects could potentially facilitate software managers to assess the overall quality of a crowdsourced project con-sisting of programming contests.