TableVista - Hard Questions: leaderboard
Accuracy on the hard questions, which need multi-hop aggregation (Web-style rendering), of 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 hard questions (most reasoning steps, multi-hop aggregation) of the 3,000 TableVista questions, Web rendering, 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 | 47 | #135 |
| 2 | GPT-5.4 Mini | Non-reasoning | 35.2 | #406 |
| 3 | Llama 4 Maverick Instruct FP8 | 24.4 | #1023 | |
| 4 | Qwen 2.5 VL 72B Instruct | 22.1 | #841 | |
| 5 | Gemma 4 31B (IT) | 21.9 | #350 | |
| 6 | Qwen 3.5 27B | Non-reasoning | 19.6 | #375 |
| 7 | Qwen 2.5 VL 32B Instruct | 19.4 | #1062 | |
| 8 | Qwen 3.5 122B A10B | Non-reasoning | 18.9 | #346 |
| 9 | Llama 4 Scout Instruct | 18.8 | #1579 | |
| 10 | Gemma 4 26B A4B (IT) | 16.6 | #556 | |
| 11 | Qwen 3.6 35B A3B | Non-reasoning | 16.4 | #481 |
| 12 | Qwen 3 VL 30B A3B Instruct | 14.8 | #895 | |
| 13 | Qwen 2.5 VL 7B Instruct | 14.2 | #1902 | |
| 14 | Gemma 3 27B (IT) | 14.1 | #1324 | |
| 15 | Qwen 3.5 9B | Non-reasoning | 14.1 | #828 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=tablevista-hard-questions · How It Works · Data refreshed daily, snapshot 2026-11-21.