Background: Natural and intuitive interfaces that monitor and promote upper limb task-specific training need to be developed. This article presents the development and testing of a touch-based game system for training and assessment of unilateral (ULR) and bilateral (BLR) reaching movements. Interaction becomes intuitive and simple by introducing in-game touch and pressure onto virtual targets projected on a custom-made large touch panel. Materials and Methods: A custom-made App integrates exergames and a biomechanical model with advanced algorithms for movement analysis. It processes and manages data from a motion-tracking sensor and a large touch panel equipped with 1222 (26 × 47) piezoresistive sensors, including high-speed readout electronics and algorithms to measure touch points and contact forces during fingertip interaction. An experiment was conducted to evaluate the experience, motivation, and movements of healthy and stroke subjects when interacting with the proposed system. The panel height, dispersion of virtual targets, and required contact force were customized based on motor skills of each group of subjects. Results: Both groups of subjects showed high level of motivation and user experience when interacting with the virtual environments. Stroke subjects performed the task slower and traveled a similar path length than healthy subjects, but with shorter range of motion. The mechanical work and potential energy profiles of both groups are consistent with those achieved when reaching real objects. Conclusions: The proposed contact-based exergames are a feasible solution for performing natural and intuitive therapeutic ULR and BLR exercises. They elicit appropriate reaching movements and contact forces in healthy and stroke subjects. The spatial and temporal attributes of the proposed solution can be customized to influence the movement and energy expenditure of specific joints.