EduArt is a new benchmark of 871 educational questions that reveals multimodal LLMs perform near ceiling on multiple-choice art history items but drop sharply on open completion and error identification tasks.
Benchmarking Vision-Language and Multimodal Large Language Models in Zero-shot and Few-shot Scenarios: A study on Christian Iconography , url =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
EduArt: An educational-level benchmark for evaluating art history knowledge in large language models
EduArt is a new benchmark of 871 educational questions that reveals multimodal LLMs perform near ceiling on multiple-choice art history items but drop sharply on open completion and error identification tasks.