TableVision - Structure: leaderboard

TableVision (2026) category of questions over images of hierarchical tables: L1 perception, identifying the table's hierarchical header structure (114 questions). Exact-match accuracy (%), zero-shot; higher is better.

Metric: Exact-match accuracy (%) on L1 perception, identifying the table's hierarchical header structure (114 questions), zero-shot, the model answers directly from the table image; TableVision test set; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 10 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Qwen 3 VL 8B Instruct90.4#1043
2Glyph78.1
3MiniCPM-V-2.666.7#3311
4DeepSeek-VL261.4#3056
5LLaVA-OneVision-7B50#3002
6InternVL3-8B48.2#1795
7GLM-4.1V-9B41.2#1134
8HiPPO39.5
9Phi-3.5-Vision Instruct20.2#6279
10Ovis2.5-9B20.2#1235

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

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