We present SciArena, an open and collaborative platform for evaluating foundation models on scientific literature-grounded tasks. Unlike traditional benchmarks for scientific literature understanding and synthesis, SciArena engages the research community directly, following the Chatbot Arena evaluation approach of community voting on model comparisons. By leveraging collective intelligence, SciArena offers a community-driven evaluation of model performance on open-ended scientific tasks that demand literature-grounded, long-form responses. The platform currently supports 47 foundation models and has collected over 20,000 votes from human researchers across diverse scientific domains. Our analysis of the data collected so far confirms its high quality. We discuss the results and insights based on the model ranking leaderboard. To further promote research in building model-based automated evaluation systems for literature tasks, we release SciArena-Eval, a meta-evaluation benchmark based on collected preference data. It measures the accuracy of models in judging answer quality by comparing their pairwise assessments with human votes. Our experiments highlight the benchmark's challenges and emphasize the need for more reliable automated evaluation methods.
@article{arxiv.2507.01001,
title = {SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Tasks},
author = {Yilun Zhao and Kaiyan Zhang and Tiansheng Hu and Sihong Wu and Ronan Le Bras and Charles McGrady and Taira Anderson and Jonathan Bragg and Joseph Chee Chang and Jesse Dodge and Matt Latzke and Yixin Liu and Xiangru Tang and Zihang Wang and Chen Zhao and Hannaneh Hajishirzi and Doug Downey and Arman Cohan},
journal= {arXiv preprint arXiv:2507.01001},
year = {2026}
}