Appear2Meaning - Origin: leaderboard

Appear2Meaning (2026) tests whether vision-language models infer structured cultural metadata from an image of a museum object, over Getty and Metropolitan Museum objects from East Asia, the ancient Mediterranean, Europe and the Americas, judged against the museum records. Accuracy of the predicted origin field in percent; higher is better.

Metric: Origin attribute accuracy (%, times 100; judged correct) on the Appear2Meaning benchmark (750 Getty and Met museum objects, 50 per culture-type combination over four cultural regions and four object types; image-only input, structured JSON prediction; GPT-4.1-mini judge against the museum metadata); higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 9 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Qwen3-VL-Flash24.1#734
2Qwen-VL-Max20.3#1402
3GPT-4.1 Mini17.3#799
4Qwen 3 VL 8B Instruct16.8#1043
5Qwen 3 VL 32B Instruct15.4#607
6Pixtral-12B13.2#2611
7GPT-5.4 Mini12#409
8Claude Haiku 4.511.8#587
9Qwen 3 VL Plus8.9#514

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=appear2meaning-origin · How It Works · Data refreshed daily, snapshot 2026-11-22.