---
base_model:
- nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16
datasets:
- OpenResearcher/OpenResearcher-Dataset
library_name: transformers
license: mit
pipeline_tag: text-generation
---
🤗 HuggingFace ｜
Blog ｜ 
Slack | 
WeChat
## OpenResearcher-30B-A3B Overview
OpenResearcher-30B-A3B is an agentic large language model designed for long-horizon deep research, presented in the paper [OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis](https://huggingface.co/papers/2603.20278).
It is fine-tuned from [NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16) on 96K [OpenResearcher dataset](https://huggingface.co/datasets/OpenResearcher/OpenResearcher-Dataset) with **100+** turns. The dataset is derived by distilling GPT-OSS-120B with [native browser tools](https://docs.vllm.ai/projects/recipes/en/latest/OpenAI/GPT-OSS.html#usage:~:text=Limitation%20section%20below.-,Tool%20Use,-%C2%B6). More info can be found on the dataset card at [OpenResearcher dataset](https://huggingface.co/datasets/OpenResearcher/OpenResearcher-Dataset).
The model achieves an impressive **54.8%** accuracy on [BrowseComp-Plus](https://huggingface.co/spaces/Tevatron/BrowseComp-Plus), surpassing performance of `GPT-4.1`, `Claude-Opus-4`, `Gemini-2.5-Pro`, `DeepSeek-R1` and `Tongyi-DeepResearch`.
## Deep Research Benchmark Results
## Evaluate OpenResearcher-30B-A3B
We evaluate OpenResearcher-30B-A3B across a range of deep research benchmarks, including BrowseComp-Plus, BrowseComp, GAIA, xbench-DeepSearch. Please find more details in [GitHub](https://github.com/TIGER-AI-Lab/OpenResearcher?tab=readme-ov-file#-benchmark-openresearcher).
## Sample Usage
The following example demonstrates how to use `OpenResearcher-30B-A3B` for deep research within its agentic environment. This requires the tools and environment setup provided in the [official GitHub repository](https://github.com/TIGER-AI-Lab/OpenResearcher).
```python
import asyncio
from deploy_agent import run_one, BrowserPool
from utils.openai_generator import OpenAIAsyncGenerator
async def main():
# Initialize generator and browser
generator = OpenAIAsyncGenerator(
base_url="http://localhost:8001/v1",
model_name="OpenResearcher/OpenResearcher-30B-A3B",
use_native_tools=True
)
browser_pool = BrowserPool(search_url=None, browser_backend="serper")
# Run deep research
await run_one(
question="What is the latest news about OpenAI?",
qid="quick_start",
generator=generator,
browser_pool=browser_pool,
)
browser_pool.cleanup("quick_start")
if __name__ == "__main__":
asyncio.run(main())
```
## Citation
```bibtex
@article{li2026openresearcher,
title={{OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis}},
author={Li, Zhuofeng and Jiang, Dongfu and Ma, Xueguang and Zhang, Haoxiang and Nie, Ping and Zhang, Yuyu and Zou, Kai and Xie, Jianwen and Yu Zhang and Wenhu Chen},
journal={arXiv preprint arXiv:2603.20278},
year={2026}
}
``` 
