Stochastic computing (SC) is a renewing computing paradigm that differs from weighted binary ones. It operates on binary stochastic bitstreams, or called stochastic numbers (SNs), instead of binary numbers (BNs). This work proposes circuits based on multiplexers (MUXs) to address the issue of SC in computing nonlinear functions. These circuits significantly reduce the number of required stochastic number generators (SNGs) and shorten critical path delay (CPD), thereby lowering hardware costs. Simulation and experimental results demonstrate that the proposed designs outperform existing designs in both computing accuracy and hardware overhead. For example, the proposed design for sin(x) using a 3rd-order Maclaurin series achieves averaged reductions of 66.84% in mean square error (MSE) and 24.62% in power-delay product (PDP), respectively, compared with previous designs.