This report synthesises findings from 10 peer-reviewed papers addressing the following research question: How do multimodal models trained on synthetic environments compare to single-modality models in terms of RoboWatch benchmark scores across varying degrees of domain shift. 11 claims were extracted from source literature; 11 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.7/10. This report is a machine-generated literature synthesis and does not constitute original research.Research goal: How do multimodal models trained on synthetic environments compare to single-modality models in terms of RoboWatch benchmark scores across varying degrees of domain shift?Autonomous literature synthesis. Automated review score: 8.7/10. Full text and citation available at Assignee Research.