TableVision - Comparison: leaderboard

TableVision (2026) category of questions over images of hierarchical tables: L2 reasoning, comparing located values (113 questions). Exact-match accuracy (%), zero-shot; higher is better.

Metric: Exact-match accuracy (%) on L2 reasoning, comparing located values (113 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
1HiPPO65.5
2Qwen 3 VL 8B Instruct62.3#1029
3Ovis2.5-9B61.9#1225
4MiniCPM-V-2.658.4#3267
5Glyph58.4
6GLM-4.1V-9B53.1#1125
7DeepSeek-VL236.3#2927
8InternVL3-8B27.4#1782
9LLaVA-OneVision-7B21.2#2981
10Phi-3.5-Vision Instruct10.6#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-comparison · How It Works · Data refreshed daily, snapshot 2026-11-21.