Objective To investigate the clinical value of the latency of the P600-like event-related potential component during a spatial N-back task as a neurophysiological indicator for differentiating children with attention deficit hyperactivity disorder (ADHD) alone from those with ADHD comorbid with developmental dyslexia (DD). Methods In this prospective study, 66 ADHD children aged 6-10 years were enrolled from the Department of Child Health Care, Second Xiangya Hospital of Central South University between June and September 2025, including 28 with ADHD alone and 38 with ADHD+DD. An additional 20 healthy children were included solely as a visual reference for electroencephalogram (EEG) topographic mapping. Behavioral symptoms were assessed using the SNAP-IV, the Childhood Executive Functioning Inventory, the Conners Child Behavior Scale, and the Dyslexia Checklist for Chinese Children. EEG was recorded during a spatial N-back task, and the P600-like component was extracted from Fz, Cz, and Pz electrodes. A linear mixed model was applied to analyze the interactions among group, electrode site, and task load. Receiver operating characteristic (ROC) curves were used to evaluate discriminative performance, and 5-fold cross-validation was conducted to reduce overfitting risk. Results Under the 1-back condition, the latency of the P600-like component at Pz was significantly longer in the ADHD+DD group than in the ADHD-alone group (P<0.001). The area under the curve (AUC) for the P600-like component latency at Pz in distinguishing ADHD alone from ADHD+DD was 0.804 (95%CI: 0.697-0.910). Using a cut-off value of 688 ms, sensitivity was 63.2% and specificity 96.4%. Hierarchical logistic regression analysis showed that model 4 (P600-like component latency + N1 reaction time + age) achieved an AUC of 0.804, comparable to that of model 2 (model 1 + P600-like component peak value + P600-like component average amplitude; AUC=0.805), with superior cross-validation stability. Conclusions The latency of the P600-like component at the Pz electrode during an N-back task may serve as a neurophysiological indicator to assist in differentiating whether children with ADHD have comorbid DD. A parsimonious model incorporating this indicator has discriminative performance comparable to the full-indicator model, with superior cross-validation stability.