WRBench public release: paper, prompts, videos, scores, human labels, and leaderboard.
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
WRBench
Hugging Face Collection · Project page · GitHub · Paper
WRBench is an open benchmark for camera-controlled video world models and diagnostic D1-D6 evaluation, introduced in Current World Models Lack a Persistent State Core.
Start here
- Leaderboard — Interactive comparison of the current public scores.
- Natural-25 inputs — Prompts, first frames, and paper-input provenance.
- Results and addenda — Rolling model-level scores and the frozen paper table.
- Generated videos and scores — Model outputs with per-video scores and provenance.
- Human annotations — Human comparison labels and associated review clips.
The paper reports a frozen benchmark table. The Hugging Face results dataset and leaderboard can be refreshed as new public results are released, so current model, video, and support counts should be read from the data files.
models 0
None public yet