Self-Ensembling Vision-Language Models for Cha: leaderboard
Charts effectively convey quantitative information, but the underlying data are often locked in image form, hindering reuse and analysis. Manually digitizing charts is time-consuming and error-prone, motivating automatic chart-to-table extraction. Recent approaches use specialized vision-language models (VLMs), yet performance still lags on charts with many datapoints or substantial stylistic vari
Metric: ChartQA (self-reported). Source: benchmarklist.com. Saturation forecast: Around April 2027. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 88.23 | #152 |
| 2 | Claude Opus 4.6 | 87.71 | #63 |
| 3 | GPT-5.1 | 84.8 | #135 |
| 4 | Seed 1.6 Flash | 81.62 | #436 |
| 5 | Llama 4 Scout | 75.13 | #656 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=self-ensembling-vision-language-models-for-cha · How It Works · Data refreshed daily, snapshot 2026-10-20.