Context: Software effort estimation (SEE) plays a key role in predicting the effort needed to complete software development task. However, the conclusion instability across learners has affected the implementation of SEE models. This instability can be attributed to the lack of an effort classification benchmark that software researchers and practitioners can use to facilitate and interpret prediction results. Objective: To ameliorate the conclusion instability challenge by introducing a classification and self-guided interpretation scheme for SEE. Method: We first used the density quantile function to discretise the effort recorded in 14 datasets into three classes (high, low and moderate) and built regression models for these datasets. The results of the regression models were an effort estimate, termed output 1, which was then classified into an effort class, termed output 2. We refertothe models generated inthis study as duplex output models as they return twooutputs. Theintroduced duplex output models trained with the leave-one-out cross validation and evaluated with MAE, BMMRE and adjusted R2, can be used to predict both the software effort and the class of software effort estimate. Robust statistical tests (Welch's t-test and Kruskal-Wallis H-test) were used to examine the statistical significant differences in the models’ prediction performances. Results: Weobserved the following: (1) the duplex output models not only predicted the effort estimates, they also offeredaguidetointerpretingtheeffortexpended; (2)incorporatingthegeneticsearch algorithmintothe duplex output model allowed the sampling of relevant features for improved prediction accuracy; and (3) ElasticNet, a hybrid regression, provided superior prediction accuracy over the ATLM, the state-of-the-art baseline regression. Conclusion: The results show that the duplex output model provides a self-guided benchmark for interpreting estimated software effort. ElasticNet can also serve as a baseline model for SEE.