TableVista - Structural Noise: leaderboard
Accuracy under the Structural Noise rendering (faded gridlines and geometric warping) of all questions in TableVista (2026), a multimodal table reasoning benchmark in which models answer questions about rendered table images directly with thinking disabled, scored by exact match backed by a semantic-equivalence check. Percent; higher is better.
Metric: Accuracy (%) on the 3,000 TableVista questions under the Structural Noise rendering (faded gridlines and geometric warping), direct-output prompt with thinking disabled (reasoning effort none for the GPT models), exact match with a GPT-5-mini semantic-equivalence check on exact-match failures; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 29 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-5.4 | Non-reasoning | 70.4 | #138 |
| 2 | Qwen 2.5 VL 72B Instruct | 54.4 | #849 | |
| 3 | Llama 4 Maverick Instruct FP8 | 54.4 | #1034 | |
| 4 | Gemma 4 31B (IT) | 53.3 | #354 | |
| 5 | Qwen 2.5 VL 32B Instruct | 49.1 | #1065 | |
| 6 | Qwen 3.5 122B A10B | Non-reasoning | 48.7 | #350 |
| 7 | GPT-5.4 Mini | Non-reasoning | 48.4 | #409 |
| 8 | Llama 4 Scout Instruct | 48.3 | #1580 | |
| 9 | Qwen 3.5 27B | Non-reasoning | 47.3 | #380 |
| 10 | InternVL3.5-14B | 45.2 | #1519 | |
| 11 | InternVL3.5-30B-A3B | 44.9 | #1269 | |
| 12 | Gemma 4 26B A4B (IT) | 43.4 | #563 | |
| 13 | Qwen 2.5 VL 7B Instruct | 42.1 | #1919 | |
| 14 | Qwen 3 VL 8B Instruct | 41.9 | #1043 | |
| 15 | Qwen 3 VL 30B A3B Instruct | 41.8 | #903 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=tablevista-structural-noise · How It Works · Data refreshed daily, snapshot 2026-11-22.