UnityBench-Mini3D: A benchmark for evaluating LLM agents' Unity 3D development
What happened
Researchers including Yijun Zhou have released UnityBench-Mini3D, a benchmark for evaluating the Unity 3D game development capabilities of LLM coding agents. It contains 77 project-level Unity tasks, organized by seven expert-defined skill categories rather than by tutorial or game genre, and split into three difficulty levels. Each task comes with 1,178 hand-written milestone tests that award partial credit and pinpoint where an agent fails. According to the paper, across tests of 21 models and 9 coding frameworks, the average pass rate was 80.9% on easy tasks, dropping to 35.2% on hard tasks, with an overall rate of 57.7%. These are test results self-reported by the paper's authors.
AI-written from the coverage · updated 25 d ago
Coverage timeline
Follow the coverage to see the story from different sides.
- arXiv Game AIPickUnityBench-Mini3D: Evaluating LLM agents for Unity 3D game development
Researchers propose UnityBench-Mini3D, which uses 77 project-level Unity tasks to evaluate the 3D game development capabilities of LLM coding agents. Each task comes with 1,178 hand-written milestone tests that award partial credit and pinpoint where failures occur. Across tests of 21 models and 9 coding frameworks, the average pass rate was 80.9% on easy tasks, dropping to 35.2% on hard tasks, with an overall rate of 57.7%.