Heterogeneity of treatment response is common in children with autism spectrum disorder. Thus, many providers vary the intervention used based on child characteristics and learning domain. An improved understanding of how to match treatments to different children and domain areas may enhance efforts to individualize treatment and improve treatment response. This study evaluated the relative efficacy of discrete trial training and pivotal response training for teaching young children at risk for autism spectrum disorder receptive and expressive language, play, and imitation skills. Using a single-subject adapted alternating treatments design, children received both the treatments for 12 weeks. Data were collected during treatment and at 3-month follow-up. All participants acquired target skills in both treatments and demonstrated some generalization, maintenance, and spontaneous skill use. Pivotal response training and discrete trial training were each more effective for some children and domains. The results suggest that early rates of learning may be predictive of longer-term treatment response and useful in informing treatment decisions.