Benchmark	Metric	Score
BrowseComp	avg@3	40.0
Mind2Web 2	avg@3	24.3
HLE	avg@3	36.2
DeepResearch Bench	avg@3	22.0
BrowseComp-Plus	avg@3	52.1
WideSearch	Item F1 avg@4	55.0
GAIA	avg@3	77.7
LiveResearchBench	avg@3	62.1

QUEST Family

Type	Resources
35B checkpoints	RL, MT+SFT, MT, SFT
30B checkpoints	RL, MT+SFT, SFT
Smaller checkpoints	9B, 4B, 2B
Training data	RL data, SFT objective data, SFT open-ended data, Mid-training data

Model selection note: if you only need to evaluate objective tasks and do not need open-ended task evaluation, we recommend the MT+SFT checkpoints because they perform better on reasoning-heavy objective benchmarks. For a more comprehensive evaluation across both objective and open-ended tasks, we recommend the RL checkpoints.

Quick start

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "osunlp/QUEST-4B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, device_map="auto", torch_dtype="auto",
)

Apply the model's chat template with tokenizer.apply_chat_template(...) before passing prompts.

License

Released under the Apache License 2.0.

Citation

If our paper or related resources prove valuable to your research, we kindly ask for a citation.

bibtex

@misc{xie2026quest,
  title={QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks},
  author={Xie, Jian and Lin, Tianhe and Wang, Zilu and Ning, Yuting and Yao, Yuekun and Xue, Tianci and Zhang, Zhehao and Li, Zhongyang and Zhang, Kai and Wu, Yufan and Chen, Shijie and Gou, Boyu and Han, Mingzhe and Wang, Yifei and Lee, Vint and Wei, Xinpeng and Wang, Xiangjun and Su, Yu and Sun, Huan},
  journal={arXiv preprint arXiv:2605.24218},
  year={2026}
}