TableVision - Listing: leaderboard

TableVision (2026) category of questions over images of hierarchical tables: L1 perception, listing operations over located cells (28 questions). Exact-match accuracy (%), zero-shot; higher is better.

Metric: Exact-match accuracy (%) on L1 perception, listing operations over located cells (28 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
1Glyph82.1
2Ovis2.5-9B75#1235
3Qwen 3 VL 8B Instruct59.3#1043
4MiniCPM-V-2.657.1#3311
5GLM-4.1V-9B42.9#1134
6HiPPO39.3
7InternVL3-8B25#1795
8LLaVA-OneVision-7B21.4#3002
9Phi-3.5-Vision Instruct21.4#6279
10DeepSeek-VL217.9#3056

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

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