TableVision - Arithmetic: leaderboard
TableVision (2026) category of questions over images of hierarchical tables: L2 reasoning, arithmetic on located values (48 questions). Exact-match accuracy (%), zero-shot; higher is better.
Metric: Exact-match accuracy (%) on L2 reasoning, arithmetic on located values (48 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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 VL 8B Instruct | 77.6 | #1043 |
| 2 | GLM-4.1V-9B | 75 | #1134 |
| 3 | Ovis2.5-9B | 68.8 | #1235 |
| 4 | Glyph | 60.4 | |
| 5 | HiPPO | 60.4 | |
| 6 | MiniCPM-V-2.6 | 54.2 | #3311 |
| 7 | DeepSeek-VL2 | 50 | #3056 |
| 8 | LLaVA-OneVision-7B | 29.2 | #3002 |
| 9 | InternVL3-8B | 20.8 | #1795 |
| 10 | Phi-3.5-Vision Instruct | 4.2 | #6279 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=tablevision-arithmetic · How It Works · Data refreshed daily, snapshot 2026-11-22.