---
license: apache-2.0
datasets:
- Multiverse4FM/Multiverse-1K-mixed
- Multiverse4FM/Multiverse-1K
- simplescaling/s1K-1.1
base_model:
- Qwen/Qwen2.5-32B-Instruct
pipeline_tag: text-generation
library_name: transformers
---

# Model Summary

> Multiverse-32B, built on [Multiverse](https://multiverse4fm.github.io/), is the first open-source, non-AR model to achieve scores of 54% and 46% on AIME 2024 & 2025.

- **Webpage:** [Multiverse](https://multiverse4fm.github.io/)
- **Paper:** [https://arxiv.org/abs/2506.09991](https://arxiv.org/abs/2506.09991)

# Use

The model usage is documented [here](https://github.com/Multiverse4FM/Multiverse).

# Evaluation

| Model | AIME24 | AIME25 | MATH500 | GPQA-Diamond |
| :--- | :---: | :---: | :---: | :---: |
| s1-32B | 35.4 | 25.8 | 88.6 | 48.0 |
| s1.1-32B | 52.9 | 41.7 | 93.4 | 62.6 |
| Qwen2.5-32B-Instruct | 15.8 | 10.4 | 80.4 | 47.0 |
| Autoregressive-32B | **54.6** | <u>45.0</u> | **92.8** | <u>61.6</u> |
| **Multiverse-32B-zero** | 52.1 | 44.2 | <u>92.4</u> | **63.6** |
| **Multiverse-32B** | 53.8 | **45.8** | 91.8 | 60.7 |

# Acknowledge

Thanks to the amazing s1 team for their s1.1 dataset as base data, and the Qwen team for their Qwen-2.5-32B-Instruct as base model.

# Citation Information

```bibtex
@misc{yang2025multiverselanguagemodelssecretly,
      title={Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation}, 
      author={Xinyu Yang and Yuwei An and Hongyi Liu and Tianqi Chen and Beidi Chen},
      year={2025},
      eprint={2506.09991},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2506.09991}, 
}
```