CArtBench: Evaluating Vision-Language Models on Chinese Art Understanding, Interpretation, and Authenticity

TL;DR

CARTBENCH is a comprehensive benchmark for evaluating Chinese art understanding, interpretation, and authenticity reasoning in vision-language models, revealing significant gaps in current model capabilities.

Contribution

It introduces four novel subtasks tailored for Chinese artworks, aligning museum data with expert standards to assess diverse reasoning skills in VLMs.

Findings

High overall accuracy masks difficulty in evidence linking and style inference

Models perform poorly on expert-style appreciation tasks

Authenticity discrimination remains near chance levels

Abstract

We introduce CARTBENCH, a museum-grounded benchmark for evaluating vision-language models (VLMs) on Chinese artworks beyond short-form recognition and QA. CARTBENCH comprises four subtasks: CURATORQA for evidence-grounded recognition and reasoning, CATALOGCAPTION for structured four-section expert-style appreciation, REINTERPRET for defensible reinterpretation with expert ratings, and CONNOISSEURPAIRS for diagnostic authenticity discrimination under visually similar confounds. CARTBENCH is built by aligning image-bearing Palace Museum objects from Wikidata with authoritative catalog pages, spanning five art categories across multiple dynasties. Across nine representative VLMs, we find that high overall CURATORQA accuracy can mask sharp drops on hard evidence linking and style-to-period inference; long-form appreciation remains far from expert references; and authenticity-oriented diagnostic discrimination stays near chance, underscoring the difficulty of connoisseur-level reasoning for current models.