CArtBench - CuratorQA (Sculpture): leaderboard

Chinese art understanding on the questions on sculptures of CuratorQA, the curator-style question task of CArtBench (2026): multiple-choice and true-or-false questions generated from Palace Museum catalog text and audited by an art expert, answered from the artwork image. Exact-match accuracy in percent; higher is better.

Metric: Exact-match accuracy (%) on the sculpture CuratorQA questions of CArtBench (Palace Museum artworks with catalog-grounded multiple-choice and true-or-false questions, answered from the artwork image, constrained decoding, temperature 0); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 9 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Qwen 3 VL 235B A22B (Thinking)84#459
2Qwen 2.5 VL 72B80#781
3Qwen 3 VL 30B A3B80#784
4GPT-5 Mini78#364
5Qwen 2.5 VL 32B78#941
6Qwen 2.5 VL 7B75#1862
7GLM-4.5V57#754
8GPT-5 Nano56#906
9Gemini 2.5 Flash48#463

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=cartbench-curatorqa-sculpture · How It Works · Data refreshed daily, snapshot 2026-11-21.