<p>Traditional stress–strength reliability analysis often assumes independence between stress and strength variables, which may not hold in practical systems. In this study, we develop a unified inferential framework for estimating the reliability parameter under dependent conditions by combining generalized exponential (GE) marginals with three copula families: Farlie–Gumbel–Morgenstern (FGM), Plackett, and Gumbel–Hougaard (GH). Estimation is performed using maximum likelihood, bootstrap, and Bayesian approaches under various loss functions via a Metropolis-within-Gibbs sampler. Performance of the estimators is evaluated through a comprehensive Monte Carlo study, examining bias and mean squared error under varying dependence strengths. The framework is applied to two real datasets from distinct domains: COVID-19 mortality and recovery ratios, and concrete carbonation depth versus concrete strength measurements. These applications demonstrate the interpretability, flexibility, and robustness of the stress–strength reliability framework in both epidemiological and engineering contexts. Overall, the proposed approach integrates flexible marginal distributions and dependence modeling into a coherent, comprehensive methodology for reliability analysis under dependence, providing accurate and interpretable estimates of <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\( R \)</EquationSource> <EquationSource Format="MATHML"><math> <mi>R</mi> </math></EquationSource> </InlineEquation>.</p>