EduMARS: Can Vision-Language Models Grade Like Teachers? Benchmarking Multimodal, Rubric-Based Assessment on Chinese K-12 Answers
Year: 2026
Type: conference-paper
Abstract: Automated grading of student work is a critical application of AI in education.However, existing benchmarks fall short in evaluating models on realistic, cognitively demanding tasks.Most rely on synthetic, well-structured text inputs, overlooking the multimodal, error-prone, and often handwritten nature of real student responses, especially in K-12 settings.We introduce EduMARS, a multimodal benchmark designed for rubric-aligned evaluation of real Chinese K-12 student answers.The dataset contains over 4,500 authentic responses from high-stakes exams across eight subjects, featuring noisy handwriting, mixed-layout diagrams, mathematical expressions, and narrative reasoning.Each response is meticulously annotated by expert teachers using step-wise scoring rubrics, error classifications, and keypoint mappings, providing fine-grained supervision aligned with real-world pedagogical practices.We evaluated existing SOTA MLLMs across the dimensions of final score and the reasoning process of grading, reveals a significant gap between existing SOTA MLLMs and human-level performance.To bridge this performance gap, we propose the Retrieval-Augmented Adaptive-Rubric Grading (RARG), enabling models to emulate expert grading logic by dynamically synthesizing case-specific evaluation schemas.RARG effectively enhances the performance and interpretability of various MLLMs on EduMARS, surpassing incontext learning and chain-of-thought.
Institution: Xi'an Jiaotong University
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W7166864606