CArtBench - CuratorQA: leaderboard
Chinese art understanding on 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, over all 14,421 questions on 1,589 artworks. Exact-match accuracy in percent; higher is better.
Metric: Exact-match accuracy (%) on all 14,421 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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 VL 235B A22B (Thinking) | 84 | #459 |
| 2 | Qwen 2.5 VL 72B | 81 | #781 |
| 3 | Qwen 2.5 VL 32B | 80 | #941 |
| 4 | Qwen 3 VL 30B A3B | 80 | #784 |
| 5 | GPT-5 Mini | 79 | #364 |
| 6 | Qwen 2.5 VL 7B | 76 | #1862 |
| 7 | GPT-5 Nano | 59 | #906 |
| 8 | GLM-4.5V | 57 | #754 |
| 9 | Gemini 2.5 Flash | 48 | #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 · How It Works · Data refreshed daily, snapshot 2026-11-21.