SWE-Game: Can Coding Agents Build the Games We Want?

SWE-Game is a benchmark comprising 247 tasks based on 41 Godot games across 13 gameplay categories, testing coding agents on tasks such as brief-to-game, design-document implementation, skeleton completion, fault repair, and Godot-to-Unity porting. Evaluation uses engine-state checks, replay of certified reference inputs, and agent-authored demonstrations to judge mechanic correctness, playability, and post-repair behavior, supplemented by vision‑language rubrics for presentation. Across six models, Opus5 leads but overall scores stay below 60/100, highlighting common issues like omitted requirements and gameplay logic errors.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• agents
• multimodal
• benchmarks