IndoTabVQA - English: leaderboard

IndoTabVQA (2026) asks questions about tables in real Bahasa Indonesia document images (bordered, borderless and colorful tables). This board uses the English questions, a cross-lingual setting: zero-shot In-Match accuracy, the normalized gold answer found inside the answer of the model, in percent; higher is better.

Metric: In-Match accuracy (%), the normalized gold answer found inside the model's answer, for English 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. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-4o44.6#751
2Qwen 2.5 VL 7B36.2#1862
3IndoTabVQA Llama-3.2-11B-Vision (checkpoint unspecified)30.8
4Qwen 2.5 VL 3B28.7#2639
5Gemma 3 12B27.4#2059
6Donut (IndoTabVQA checkpoint unspecified)5.48

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

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