Across four image-based physics concept inventories, tested AI models scored between 21% and 81.5% accuracy, and cheaper models often matched or beat far more expensive ones.
Dataset on Zenodo (2025)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
physics.ed-ph 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Multimodal large language models and physics visual tasks: comparative analysis of performance and costs
Across four image-based physics concept inventories, tested AI models scored between 21% and 81.5% accuracy, and cheaper models often matched or beat far more expensive ones.