Space debris poses a significant risk to future missions, highlighting the need for more efficient identification methods. This paper introduces the RoBo6 dataset for rocket body classification based on light curves, as no standardized benchmark exists. The dataset, derived from the Mini Mega Tortora database, includes light curves for six rocket body classes: CZ-3B, Atlas 5 Centaur, Falcon 9, H-2A, Ariane 5, and Delta 4. With 5,676 training and 1,404 test samples, it addresses data inconsistencies using resampling, normalization, and filtering techniques. Several machine learning models were evaluated, including CNNs and transformer-based approaches, with Astroconformer achieving the highest accuracy. The dataset establishes a common benchmark for future comparisons and advancements in rocket body classification tasks.