MoveBench Benchmarks LLMs for Sports and Health Coaching
MoveBench is a rubric-based benchmark for evaluating large language models in sports and health coaching, combining multiple-choice questions with open-ended answers grounded in real-world scenarios. The paper evaluated 15 LLMs on 809 questions and 5,012 rubric-level criteria, with the authors reporting substantial variation in safety awareness, program design, and personalization. It was submitted to arXiv on October 19, 2026 and revised on October 26.
MoveBench offers a domain-specific evaluation resource for assessing whether LLMs can provide safe, scientifically valid, personalized, and actionable coaching.
Computer Science > Artificial Intelligence
arXiv:2610.26185 (cs)
[Submitted on 19 Oct 2026 (v1), last revised 26 Oct 2026 (this version, v2)]
Title:MoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coaching
Authors:Yitong Li, Jiang Bian, Jingling Wang, Pan Ding, Chengying Gu
View a PDF of the paper titled MoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coaching, by Yitong Li and 4 other authors