Views
No views yet
GPT-4.1, Claude-Opus-4, Gemini-2.5-Pro, DeepSeek-R1 and Tongyi-DeepResearch. It also demonstrates leading performance across a range of deep research benchmarks, including BrowseComp, GAIA, WebWalkerQA, and xbench-DeepSearch. We fully open-source the training and evaluation recipe—including data, model, training methodology, and evaluation framework for everyone to progress deep research.Q4_K_M, Q5_0, Q5_K_M, Q6_K, and Q8_0.| Quantization | File Size | BPW | PPL | +/- | Tokens/sec |
|---|---|---|---|---|---|
| BF16 | 58.84 GiB | 16.00 | 8.4522 | 0.06489 | 4,117.90 |
| Q8_0 | 31.27 GiB | 8.51 | 8.4654 | 0.06499 | 7,490.81 |
| Q6_K | 31.20 GiB | 8.49 | 8.4784 | 0.06510 | 7,389.76 |
| Q5_0 | 20.37 GiB | 5.54 | 8.5462 | 0.06558 | 7,534.66 |
| Q4_K_M | 22.82 GiB | 6.21 | 8.5970 | 0.06610 | 7,046.96 |
| Q5_K_M | 24.24 GiB | 6.60 | 8.6074 | 0.06625 | 6,661.48 |
 Zhuofeng Li |
 Dongfu Jiang |
 Xueguang Ma |
 Haoxiang Zhang |
 Ping Nie |
1@article{li2026openresearcher,
2 title={{OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis}},
3 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 Zhang, Yu and Chen, Wenhu},
4 journal={arXiv preprint arXiv:2603.20278},
5 year={2026}
6}