This work aimed to derive new analytical formulas for the stress–strength reliability of the type $P(X<Y)$ when both $X$ and $Y$ follow Fréchet, reversed Weibull or Weibull distributions. The new expressions were given in terms of extreme value $\mathbb{H}$-functions and have been obtained under fewer parameter restrictions while compared to similar results in the literature of these distributions. The performance of the maximum likelihood estimator was evaluated through Monte-Carlo simulations and the results were compared with a nonparametric estimator. Three real dataset applications were carried out. First, we analyzed the statistical behavior of financial assets' returns, showing how $P(X<Y)$ can be used to build an interesting approach to perform asset selection. Second, minimum monthly flows of water were analyzed. Finally, we compared failure voltage levels of two types of electrical cable insulation. For all the real case applications, confidence intervals for $P(X<Y)$ were obtained by Bootstrap methods.