ArtECulture - Arabic: leaderboard
Metric: Accuracy (%; Arabic-speaking culture labels; zero-shot prediction of the majority emotion (nine categories) that the target culture perceives in each of the 679 test artworks; original models without the authors retrieval knowledge or fine-tuning). Source: arxiv.org. Saturation forecast: Around 2034. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 27B | 41.53 |
| 2 | Qwen 3.6 35B A3B | 39.76 |
| 3 | Gemini 3.5 Flash | 39.62 |
| 4 | Gemini 3 Flash | 39.18 |
| 5 | Gemma 4 31B (IT) | 38.44 |
| 6 | Qwen 3.6 27B | 38 |
| 7 | Claude Sonnet 4.6 | 35.94 |
| 8 | Claude Opus 4.8 | 33.04 |
| 9 | Qwen 3 VL 8B | 32.99 |
| 10 | GPT-5.5 | 31.96 |
| 11 | Qwen 3.5 9B | 31.22 |
| 12 | aya-vision-8B | 29.16 |
| 13 | Gemma 3 12B (IT) | 28.13 |
| 14 | Pixtral-12B | 27.69 |
Interactive version: theaggregate.ai/benchmark?slug=arteculture-arabic · How It Works · Data refreshed daily, snapshot 2026-09-26.