Qwen-VL-PRM-3B

Model Summary

Qwen-VL-PRM-3B is a process reward model finetuned from Qwen2.5-3B-Instruct on approximately 300,000 examples. It demonstrates strong test-time scaling performance improvements on various advanced multimodal reasoning benchmarks when used with Qwen2.5-VL and Gemma-3 models despite being trained mainly on abstract reasoning datasets and elementary reasoning datasets.

• Logs: https://wandb.ai/aisg-arf/multimodal-reasoning/runs/pnsncs80
• Repository: https://github.com/theogbrand/vlprm
• Paper: https://arxiv.org/pdf/2509.23250

Use

The model usage is documented here.

Evaluation

Commercial Models

Qwen-2.5-VL Family

Gemma-3 Family

Framework versions

• TRL: 0.19.1
• Transformers: 4.55.3
• Pytorch: 2.7.1
• Datasets: 3.0.1
• Tokenizers: 0.21.4

Citations

@misc{ong2025vlprms,
      title={Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned}, 
      author={Brandon Ong, Tej Deep Pala, Vernon Toh, William Chandra Tjhi, and Soujanya Poria},
      year={2025},
      eprint={2509.23250},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/pdf/2509.23250}, 
}