zhaosuifeng/FinRAGBench-V

FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domain (EMNLP 2025)

30
/ 100
Emerging

This project helps financial analysts, researchers, and data scientists evaluate how well AI models understand complex financial documents. It takes in multimodal financial reports (with text, charts, and tables) and questions, then assesses the AI's ability to provide accurate answers with clear visual citations. The output helps users understand the strengths and weaknesses of different AI models in handling real-world financial information.

Use this if you are a researcher or practitioner building and evaluating AI systems that need to accurately answer questions based on diverse financial documents, including charts and tables.

Not ideal if you are looking for an off-the-shelf financial analysis tool to use directly for market predictions or investment decisions.

financial-analysis financial-research document-intelligence AI-evaluation data-extraction
No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

12

Forks

Language

Python

License

Apache-2.0

Last pushed

Jan 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/zhaosuifeng/FinRAGBench-V"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.