---
base_model:
- open-thoughts/OpenThinker3-1.5B
library_name: transformers
license: apache-2.0
model-index:
- name: OpenThinker3-1.5B-RLVE
  results: []
pipeline_tag: text-generation
tags:
- https://arxiv.org/abs/2511.07317
---

> [!NOTE]
> For full information, go check out the RLVE paper [here](https://arxiv.org/abs/2511.07317).

# OpenThinker3 1.5B RLVE

This model is trained on top of [Openthinker3 1.5B](https://huggingface.co/open-thoughts/OpenThinker3-1.5B) using RLVE.
For more details on RLVE, check out the figure below, or see our [paper](https://arxiv.org/abs/2511.07317) for more details.

<img src="https://huggingface.co/hamishivi/OpenThinker3-1.5B-RLVE/resolve/main/Figure1.png" alt="Figure 1" width="1000"/>

# Evaluation Results

We provide evaluation instructions in [our repository](https://github.com/Zhiyuan-Zeng/RLVE).

| Benchmark | AIME 2024 (Avg@64) | AIME 2025 (Avg@64) | OMEGA-500 (Avg@4) | OlympiadBench (Avg@4) | BBEH (Avg@4) | LiveCodeBench-v6 (Pass@8) |
|:-----------|:------------------:|:------------------:|:-----------------:|:----------------------:|:-------------:|:--------------------------:|
| [OpenThinker3-1.5B](https://huggingface.co/open-thoughts/OpenThinker3-1.5B) (starting model) | 54.32 | 42.03 | 25.15 | 56.85 | 4.00 | 28.17 |
| [OpenThinker3-1.5B-RLVE](https://huggingface.co/hamishivi/OpenThinker3-1.5B-RLVE) | **58.18** | **49.90** | **29.45** | **62.67** | **7.13** | **34.07** |

# Intended uses & limitations

Apache 2.0 License

## Training

For training details and hyperparameters. please see [our repository](https://github.com/Zhiyuan-Zeng/RLVE).

In particular, you can rerun training for this model with this command (after setting up the repository):
```bash
bash scripts/training/OpenThinker3-1.5B/rlve/num-environment=400.sh RLVE
```

# Links
- 📝 [RLVE Paper](https://arxiv.org/abs/2511.07317)
- 💻 [RLVE GitHub Repository](https://github.com/Zhiyuan-Zeng/RLVE)
- 🤖 [Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE](https://huggingface.co/hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE)
- 🤖 [OpenThinker3-1.5B-RLVE](https://huggingface.co/hamishivi/OpenThinker3-1.5B-RLVE) - this model.


# Citation
```
@article{zeng2025rlve,
  title={RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments},
  author={Zeng, Zhiyuan and Ivison, Hamish and Wang, Yiping and Yuan, Lifan and Li, Shuyue Stella and Ye, Zhuorui and Li, Siting and He, Jacqueline and Zhou, Runlong and Chen, Tong and Zhao, Chenyang and Tsvetkov, Yulia and Du, Simon Shaolei and Jaques, Natasha and Peng, Hao and Koh, Pang Wei and Hajishirzi, Hannaneh},
  journal={arXiv preprint 2511.07317},
  year={2025}
}
```