This study provides a rigorous empirical comparison of structural and reduced-form credit risk frameworks. As major difference we focus on the discriminative modeling of default time. In contrast to previous literature, we calibrate both approaches to bond and equity prices. By using same input data, applying comparable estimation techniques, and assessing the out-of-sample prediction quality on same time series of CDS prices we are able to judge whether empirically the model structure itself makes an important difference. Interestingly, the models' prediction power is quite close on average. Still, the reduced-form approach outperforms the structural for investment-grade names and longer maturities.