Model Releases

ParseBench is the first benchmark to include VLM chart understanding ๐Ÿ“Š๐Ÿ“ˆ๐Ÿ“‰ over enterprise documents. ๐ŸŸ  Existing benchmarks (ChartQA, Charโ€ฆ

ParseBench is the first benchmark to include VLM chart understanding ๐Ÿ“Š๐Ÿ“ˆ๐Ÿ“‰ over enterprise documents. ๐ŸŸ  Existing benchmarks (ChartQA, ChartXiv) test over charts specifically and not the chart's inclusio

DGX agentx-post
model-releasesjerry-liu--x

ParseBench is the first benchmark to include VLM chart understanding ๐Ÿ“Š๐Ÿ“ˆ๐Ÿ“‰ over enterprise documents. ๐ŸŸ  Existing benchmarks (ChartQA, ChartXiv) test over charts specifically and not the chart's inclusion in the overall document. Also doesn't contain references to real-world docs โœ… ParseBench contains 568 pages containing a diversity of charts embedded in real-world documents. โœ… It contains a mix of charts: discrete series, continuous series, bar/point/line graphs, charts without clear markers, and more โœ… Each chart has a set of ground-truth datapoints bootstrapped with an initial model and verified through human annotators (with a tolerance) Come check it out! Blog: https://www.llamaindex.ai/blog/parsebench?utm_medium=socials&utm_source=xjl&utm_campaign=2026-apr- Paper: https://arxiv.org/abs/2604.08538?utm_medium=socials&utm_source=twitter&utm_campaign=2026-apr- Website: https://parsebench.ai/?utm_medium=socials&utm_source=xjl&utm_campaign=2026-apr- Media Let's talk parsing charts ๐Ÿ“Š๐Ÿ“ˆ. Last week we released ParseBench, the first document OCR benchmark for AI agents. New in ParseBench: ChartDataPointMatch. Most document look at a chart and OCR the caption. Agents need the actual numbers. That's the gap between "OCR'd the text arouโ€ฆ

Related

Source: Jerry Liu (X) | 2026-04-21

Loading related sourcesโ€ฆ