3D graphics editing is a crucial component in applications like movie production and game design, yet it remains a time-consuming process that demands highly specialized domain expertise. Automating the process is challenging because graphical editing requires performing different tasks, each requiring distinct skill sets. Recently, multi-modal foundation models have emerged as a powerful framework for automating the editing process, but their development and evaluation are bottlenecked by the lack of a comprehensive benchmark that requires human-level perception and real-world editing complexity. In this work, we present BlenderGym, a benchmark designed to systematically evaluate foundational model systems for 3D graphics editing with tasks capturing the various aspects of 3D editing and fixed ground-truth for evaluation. We evaluate closed- and open-source VLMs with BlenderGym and observe that even the state-of-the-art VLMs struggle with tasks relatively easily for a novice Blender user. Enabled by BlenderGym, we study how inference scaling techniques impact graphics editing tasks. Notably, our findings reveal that the verifier used to guide the scaling of generation can itself be improved through scaling, complementing recent insights on scaling of LLM generation in coding and math tasks. We further show that inference compute is not uniformly effective and can be optimized by strategically distributing it between generation and verification.