LADDER: Level Analysis Dataset for Difficulty Evaluation and Ranking
Yao Jean-Eudes Adjanohoun, Yannick Francillette, Hugo Tremblay, Bruno Bouchard · 2025
Standardized datasets are fundamental to scientific research. While fields like natural language processing and computer vision have widely accepted datasets that drive progress, video game research still lacks such resources, particularly for studying level difficulty. Existing studies rely on isolated, custom datasets, limiting cross-study comparisons and hindering the development of generalizable models. To bridge this gap, we introduce LADDER, a novel dataset specifically designed to analyze and evaluate level difficulty in video games. Unlike previous datasets that primarily focus on physiological and behavioral player data, LADDER integrates objective performance metrics (e.g., health lost, number of attempts before success), level characteristics (e.g., number of danger zones, object placement), and perceived difficulty ratings across multiple platformer games. This dataset enables researchers to establish benchmarks, enhance collaboration across disciplines, and improve study reproducibility. LADDER provides a standardized foundation for investigating the relationship between game design elements and player experience. By facilitating difficulty assessment and level balancing, it supports advancements in game design, player modeling, and adaptive gameplay systems. We present an overview of existing datasets, describe the methodology behind LADDER’s construction, and showcase its potential through preliminary analyses. The dataset is freely available online, offering a valuable resource for the scientific community to develop more engaging and accessible gaming experiences.