Joint attention (JA), a core deficit in children with autism spectrum disorder (ASD), is crucial for social interaction, emotional understanding, and cognitive development. This study aims to compare and analyze the eye-tracking data of ASD and typically developing children (TDC) during virtual games, exploring how different cue types affect JA performance in ASD children. A total of 31 TDC and 40 ASD children participated in the study. Using eye-tracking devices, we recorded the children’s eye movements as they played virtual games, selecting the correct target based on cues provided by virtual characters. Our findings revealed that different cue types significantly impacted the game scores of ASD children but had no significant effect on TDC, highlighting a notable disparity between the two groups. ASD children showed a lower fixation frequency, irregular fixation paths, and increased attention to non-target objects compared to TDC. Interestingly, among the three cue types, ASD children exhibited a preference for the third type, leading to longer fixation on the region of interest and higher game scores. These results underscore the importance of cue selection in enhancing JA in ASD children. This study provides novel insights into the JA deficits in ASD children and offers a scientific basis for the development of targeted and individualized intervention programs.