Search arXivSearch

arXiv · 2506.19662

Multimodal large language models and physics visual tasks: comparative analysis of performance and costs

Abstract

Multimodal large language models (MLLMs) capable of processing both text and visual inputs are increasingly being explored for uses in physics education, such as tutoring, formative assessment, and grading. This study evaluates a range of publicly available MLLMs on a set of standardized, image-based physics research-based conceptual assessments (concept inventories). We benchmark 15 models from three major providers (Anthropic, Google, and OpenAI) across 102 physics items, focusing on two main questions: (1) How well do these models perform on conceptual physics tasks involving visual representations? and (2) What are the financial costs associated with their use? The results show high variability in both performance and cost. The performance of the tested models ranges from 81.5% to as low as 21%. We also found that expensive models do not always outperform cheaper ones and that, depending on the demands of the context, cheaper models may be sufficiently capable for some tasks. This is especially relevant in contexts where financial resources are limited or for large-scale educational implementation of MLLMs. By providing these analyses, our aim is to inform teachers, institutions, and other educational stakeholders so that they can make evidence-based decisions about the selection of models for use in AI-supported physics education.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Giulia Polverini, Bor Gregorcic. 2025-09-11. Multimodal large language models and physics visual tasks: comparative analysis of performance and costs. https://doi.org/10.1088/1361-6404%2Fae03f8

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

Addressing misconceptions in university physics: A review and experiences from quantum physics educators

Students often begin physics courses with misconceptions rooted in everyday experience and intuition, which can be resistant to change. While research has identified strategies for addressing misconceptions across physics, it remains unclear whether different domains, like classical and quantum physics, require different approaches. Quantum concepts can pose different representational and mathematical demands, while both domains require instructors to elicit and develop students' reasoning. To support discussion of these instructional challenges, we organize selected literature on addressing misconceptions in physics education and summarize instructors' accounts. The overview groups 122 distinct works into four categories, with further subcategories. A preliminary framework developed from existing review literature informed the interview guide. We interviewed 12 instructors from the University of Waterloo's Institute for Quantum Computing and the Perimeter Institute, who have collectively taught over 100 quantum courses. The accounts describe difficulties involving instructional representations, prerequisite knowledge, and the interpretation of students' reasoning, alongside reported diagnostic and instructional responses. We draw these accounts and the literature together as questions for instructional planning. The report does not resolve the intended classical--quantum comparison or establish comparative instructional effectiveness.

physics.ed-ph

Johann Bernoulli's analysis of elastic collisions (a teaching sequence to introduce the dynamic law thereby inspired)

In order to explain an elastic collision, Johann Bernoulli considered two bodies connected by a spring. Motion is defined as a succession of states of rest. Then, considering the spring to be a lever with a body at each extremity, the laws of equilibrium imply that `motion' is described by the time variation of the (common) quantity of motion of the bodies; the dynamic law is thus deduced. This inspires a teaching sequence to introduce the dynamic law (in one dimension) in introductory physics course; we call it ``bernoullian sequence''.

physics.ed-ph

Design and Initial Evaluation of a Photovoltaics-focused Course-based Undergraduate Research Experience in Physics

Traditional physics laboratory courses often focus on experiments with well-known results, limiting students' engagement in authentic scientific practices. Course-based undergraduate research experiences (CUREs), where students engage in real research with unknown outcomes, have been shown to support positive student outcomes, such as increased self-efficacy, persistence, and engagement in scientific practices. However, discipline-specific studies of CUREs in physics remain limited. We describe the development, structure, and initial implementation of a photovoltaics-focused CURE in a second-year undergraduate physics laboratory course at the University of Colorado Boulder. To examine how students experienced the course, we analyzed end-of-semester reflection assignments using the five CURE components (i.e., scientific practices, discovery, relevance, collaboration, and iteration), as well as established dimensions of research authenticity, as analytic frameworks. Students described experiences associated with all five CURE components, with collaboration, relevance, and scientific practices appearing most prominently in their reflections. Students also associated authentic research with meaningful scientific contribution, engagement in authentic scientific practices, and navigating the uncertainty and setbacks inherent in research, although fewer explicitly identified themselves as researchers or scientists. A subset of students additionally connected the course to their immediate thinking about future academic and professional pathways. This work contributes both a discipline-specific model for implementing CUREs in experimental physics laboratory courses and provides insight into how students interpret and experience authentic research within this course context.

physics.ed-ph