Factor-model performance depends not only on the model but also on how test assets are constructed. We form characteristic-unsorted random portfolios from a broad CRSP universe and vary stock selection, initial weighting, holding, and rebalancing. Rankings shift materially: buy-and-hold favors FF5 and FF6, whereas daily constant-weighting favors FF3, the most stable model across designs. Although q5 attains the highest maximum Sharpe ratio in factor-spanning tests, it leaves comparatively large and construction-sensitive pricing errors on random portfolios. These results reflect construction-specific weighting of each model's pricing-error vector. Test-asset construction, including dynamic weight management, is therefore a design choice in model evaluation.