IndoTabVQA - Indonesian: leaderboard
Metric: In-Match accuracy (%), the normalized gold answer found inside the model's answer, for Bahasa Indonesia questions about tables in real Bahasa Indonesia document images, 1,043 test images, zero-shot; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 72.2 |
| 2 | Qwen 2.5 VL 7B | 54.8 |
| 3 | Gemma 3 12B | 40.9 |
Interactive version: theaggregate.ai/benchmark?slug=indotabvqa-indonesian · How It Works · Data refreshed daily, snapshot 2026-10-07.