README.md

---
title: DAREBench
emoji: 🦞
colorFrom: red
colorTo: blue
sdk: static
app_file: index.html
pinned: true
short_description: Deployment-Aware and Reliable Evaluation of Models as Agents
tags:
- benchmark
- agents
- openclaw
- evaluation
- leaderboard
datasets:
- SeerRay-Lab/DAREBench
thumbnail: https://seerray-lab-darebench.static.hf.space/assets/img/social-card.png
---

# DAREBench: Deployment-Aware and Reliable Evaluation of Models as Agents

Project page for DAREBench. A workload- and deployment-aware benchmark for evaluating models as agents.

- 📄 Paper: [arXiv 2609.06059](https://arxiv.org/abs/2609.06059)
- 💻 Code: [github.com/SeerRay-Lab/DareBench](https://github.com/SeerRay-Lab/DareBench)
- 🤗 Dataset: [SeerRay-Lab/DAREBench](https://huggingface.co/datasets/SeerRay-Lab/DAREBench)