---
license: apache-2.0
library_name: transformers
pipeline_tag: image-text-to-text
tags:
- video
- multimodal
- robotics
- embodied-ai
- evaluation
- qwen
---

# RoboJudge-9B

RoboJudge-9B is a multimodal judge for generated embodied-manipulation videos.
It scores two axes on a 1–5 scale:

- **Physical Adherence (PA):** agent consistency, scene consistency, and
  interaction realism.
- **Instruction Alignment (IA):** agent match, object correctness, and goal
  completion.


## Benchmark results on RoboJudge-Bench

| Metric | Pearson r with human ratings |
|---|---:|
| PA | 0.645 |
| IA | 0.775 |
| Overall | 0.719 |


## License

The RoboJudge release code and model weights are provided under Apache-2.0.
Use of the associated datasets is additionally subject to the terms of their
upstream sources.