Proposal to Add “Document Understanding” Section to the Open VLM Leaderboard

[abrahamdaniels]

Propose the addition of a “Document Understanding” section to the Open VLM Leaderboard. This new section would focus on evaluating models’ capabilities in comprehending and processing document-based information, which is a critical aspect of vision-language integration for enterprise use cases.

Proposed Benchmark Datasets to be included in Document Understanding:

• DocVQA
• ChartVQA
• TextVQA
• InfoVQA
• LiveXivVQA
• LiveXivTQA