HelenPeng/ExeWorldBench
Dataset · https://huggingface.co/datasets/HelenPeng/ExeWorldBench
ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling 📄 Paper 🌐 Project Page Overview ExeWorldBench is a benchmark for evaluating world understanding and executable realization through code-based 3D world construction. Rather than merely reproducing what a world looks like, ExeWorldBench evaluates whether models can construct an executable world that works. Usage 1. Harness-Based Evaluation For harness-based evaluation… See the full description on the dataset page: https://huggingface.co/datasets/HelenPeng/ExeWorldBench.
First seen by Oriel on .
Metric trends
Last 30 days · Up to 120 recorded samples per source and metric · First and latest retained
Likes
Total likes reported by the source.
- Hugging Face Datasets: 36, latest observation ; +16 over observed period since
Downloads (30d)
Rolling 30-day downloads. A change in this value is not new downloads during the observed period.
- Hugging Face Datasets: 664, latest observation ; +477 over observed period since
Aliases
| Source | External ID | URL |
|---|---|---|
| Hugging Face Datasets | HelenPeng/ExeWorldBench | https://huggingface.co/datasets/HelenPeng/ExeWorldBench |