# 🦁 WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild [📑 Paper](https://allenai.github.io/WildBench/WildBench_paper.pdf) | [💻 GitHub](https://github.com/allenai/WildBench) | [🤗 HuggingFace](https://huggingface.co./collections/allenai/wildbench-65e8f2fa9c1260a85a933627) | [🐦 X](https://x.com/billyuchenlin/status/1795746137875554531) | [💬 Discussion](https://huggingface.co./spaces/allenai/WildBench/discussions) | ⚙️ **Version**: **V2** | **# Models**: {model_num} | Updated: **{LAST_UPDATED}**