TableVision - Retrieval: leaderboard

TableVision (2026) category of questions over images of hierarchical tables: L1 perception, locating and reading specific cells (371 questions). Exact-match accuracy (%), zero-shot; higher is better.

Metric: Exact-match accuracy (%) on L1 perception, locating and reading specific cells (371 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
1GLM-4.1V-9B80.6#1125
2Qwen 3 VL 8B Instruct78.8#1029
3Glyph78.4
4Ovis2.5-9B76.5#1225
5HiPPO73.6
6MiniCPM-V-2.673#3267
7DeepSeek-VL261.2#2927
8LLaVA-OneVision-7B57.7#2981
9InternVL3-8B36.4#1782
10Phi-3.5-Vision Instruct24.8#6268

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

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