metadata

title: DeepResearch Bench
emoji: 🔍
colorFrom: blue
colorTo: indigo
sdk: gradio
sdk_version: 5.31.0
app_file: app.py
pinned: false
license: apache-2.0

DeepResearch Bench

DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

This application showcases comprehensive evaluation results for Deep Research Agents. The app includes:

🏆 Leaderboard - View overall performance metrics across all evaluated models
🔍 Data Viewer - Explore detailed results for individual research tasks
📊 Side-by-Side Comparison - Compare different models' responses to the same research questions

Visit our project website for more information.

Citation

@article{du2025deepresearch,
  author    = {Mingxuan Du and Benfeng Xu and Chiwei Zhu and Xiaorui Wang and Zhendong Mao},
  title     = {DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents},
  journal   = {arXiv preprint},
  year      = {2025},
}

Hugging Face Space Details

SDK: Gradio
SDK Version: 3.50.0