JAMER: Project-Level Code Framework Dataset and Benchmark on Professional Game Engines
For AI-driven game development and code generation, this benchmark reveals that current models struggle with project-level code engineering on professional game engines, providing a new evaluation standard.
The paper introduces JamSet and JamBench, the first project-level game code framework dataset and benchmark on a professional game engine (Godot), derived from Game Jam competitions. Evaluation of 9 frontier models shows a capability cliff: runtime pass rates drop from 80.4% on small projects to 5.7% on large ones, and code agents improve compilation but not runtime behavior, highlighting architectural design as the bottleneck.
Current AI-driven game development has made substantial progress in asset generation, gameplay design, and web-based game coding, yet project-level code engineering on professional game engines remains largely unexplored due to the absence of large-scale datasets and deterministic evaluation methods. We present JamSet and JamBench, the first project-level game code framework dataset and benchmark built on a professional game engine. Our key insight is that Game Jam competitions, community events where developers build complete games under tight time constraints, yield thousands of open-source projects suitable for this purpose. Building on the Godot engine's text-based format and headless execution mode, we design a deterministic verification pipeline from file integrity to runtime behavior collection, distilling 8,133 verified projects from over 240,000 repositories. Of these, 300 manually verified projects form JamBench; the rest constitute JamSet. JamBench defines theme-driven generation and code completion tasks, evaluated through a pipeline combining compilation pass rates, Structural Completeness Score (SCS), and Behavioral Alignment Score (BAS). Evaluation of 9 frontier models reveals a capability cliff as project scale increases, with runtime pass rates dropping from 80.4% on small projects to 5.7% on large ones (Task2a). Code Agents improve compilation rates yet yield no gains in runtime behavioral quality, indicating that the bottleneck lies in architectural design rather than syntactic correctness. Experiments validate JamSet as effective training data. All data and code are publicly available.