---
title: Wiki Live Challenge Leaderboard
emoji: 🏆
colorFrom: yellow
colorTo: red
sdk: gradio
sdk_version: 5.9.1
python_version: "3.11"
app_file: app.py
pinned: true
license: apache-2.0
short_description: Leaderboard for Wiki Live Challenge benchmark
---

# Wiki Live Challenge Leaderboard

A live benchmark leaderboard for evaluating Deep Research Agents on Wikipedia-quality article generation.

## Features

- **Wiki Writing Evaluation**: 39 criteria from Wikipedia's Manual of Style
  - Overall, Well-written, Neutral, Broad coverage
- **Wiki Fact Evaluation**: Factual accuracy metrics
  - Coverage against Wikipedia
  - Reference accuracy

## Links

- 🌐 **Website**: [Wiki Live Challenge](http://agentresearchlab.org/benchmarks/wiki-live-challenge/index.html#home)
- 💻 **Code**: [github.com/WangShao2000/Wiki_Live_Challenge](https://github.com/WangShao2000/Wiki_Live_Challenge)
- 📊 **Dataset**: [huggingface.co/datasets/muset-ai/Wiki_Live_Challenge](https://huggingface.co/datasets/muset-ai/Wiki_Live_Challenge)

## Citation

```bibtex
@article{wang2026wikilive,
  author    = {Shaohan Wang and Benfeng Xu and Licheng Zhang and Mingxuan Du and Chiwei Zhu and Xiaorui Wang and Zhendong Mao and Yongdong Zhang},
  title     = {Wiki Live Challenge: Challenging Deep Research Agents with Expert-Level Wikipedia Articles},
  journal   = {arXiv preprint},
  year      = {2026},
}
```