from dataclasses import dataclass from enum import Enum @dataclass class Task: benchmark: str metric: str col_name: str # Select your tasks here # --------------------------------------------------- class Tasks(Enum): # task_key, metric_key, name to display in the leaderboard task0 = Task("avg", "score", "Avg") task1 = Task("nar", "score", "Nar") task2 = Task("mt", "score", "MT") task3 = Task("con", "score", "Con") task4 = Task("if", "score", "IF") task5 = Task("scn", "score", "Scn") task6 = Task("saf", "score", "Saf") task7 = Task("att", "score", "Att") # --------------------------------------------------- # Your leaderboard name TITLE = """

🎭 RoleRMBench Leaderboard

""" # What does your leaderboard evaluate? INTRODUCTION_TEXT = """ RoleRMBench evaluates reward models on role-playing scenarios across multiple dimensions. For more information, please refer to: [https://github.com/Dear-Sloth/RoleRMBench](https://github.com/Dear-Sloth/RoleRMBench) *Feel free to submit your results to our 🤗 HuggingFace leaderboard.* """ CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results" CITATION_BUTTON_TEXT = r"""@misc{ding2025rolermbenchrolermreward, title={RoleRMBench & RoleRM: Towards Reward Modeling for Profile-Based Role Play in Dialogue Systems}, author={Hang Ding and Qiming Feng and Dongqi Liu and Qi Zhao and Tao Yao and Shuo Wang and Dongsheng Chen and Jian Li and Zhenye Gan and Jiangning Zhang and Chengjie Wang and Yabiao Wang}, year={2025}, eprint={2512.10575}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2512.10575}, }"""