The study aimed to determine the comparison of the effectiveness of an electronic visual-motor training program with task-based cognitive rehabilitation on the visual-spatial working memory of children with autism spectrum disorder. The research method was a quasi-experimental study with a pre-test-post-test design and a two-month follow-up test. The statistical population of the present study included children with autism spectrum disorder, forty-five of whom were selected by convenience sampling, and 15 children with autism spectrum disorder were randomly assigned to the visual-motor training program group, 15 to the task-based cognitive rehabilitation group, and 15 to the control group. In this study, the n-back test was used to collect data. For data analysis, the repeated-measures analysis of variance method and the Bonferroni post hoc test were used to analyze the data using SPSS 23 software. Probability values less than 0.05 were considered statistically significant. The results of the study showed that there was a significant difference between the three stages of pre-test, post-test, and follow-up in visual-spatial working memory in the experimental and control groups (p<0.001). In addition, the results of the study indicated that there was a significant difference between the experimental and control groups in visual-spatial working memory (p<0.01). The results of comparing the effectiveness of the two interventions on visual-spatial working memory showed that task-based cognitive rehabilitation was more effective than the electronic visual-motor training program (p<0.001). Based on the findings, it can be said that task-based cognitive rehabilitation and the electronic visual-motor training program are effective in improving the visual-spatial working memory of children with autism spectrum disorder.