TableVision - Multi-hop: leaderboard

TableVision (2026) category of questions over images of hierarchical tables: L3 analysis, multi-hop reasoning over several lookups (104 questions). Exact-match accuracy (%), zero-shot; higher is better.

Metric: Exact-match accuracy (%) on L3 analysis, multi-hop reasoning over several lookups (104 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
1Glyph58.7
2Qwen 3 VL 8B Instruct26#1043
3Ovis2.5-9B25#1235
4GLM-4.1V-9B13.5#1134
5DeepSeek-VL210.6#3056
6LLaVA-OneVision-7B8.7#3002
7MiniCPM-V-2.66.7#3311
8Phi-3.5-Vision Instruct4.8#6279
9HiPPO4.8
10InternVL3-8B1.9#1795

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

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