HiThink-Research/MME-Finance

[MM 2025] A Multimodal Finance Benchmark for Expert-level Understanding and Reasoning

40
/ 100
Emerging

This project helps finance professionals evaluate how well AI models understand complex financial information. It takes financial documents, like reports with candlestick charts and technical indicators, along with specific questions, and assesses an AI's ability to interpret them. Financial analysts, traders, and investment managers can use this to benchmark and select AI tools for expert-level financial reasoning.

Use this if you need to objectively measure and compare the performance of different AI models on tasks requiring deep financial understanding, including interpreting charts and specialized financial terms.

Not ideal if you are looking for an AI model to directly perform financial analysis or generate reports, as this is a tool for evaluating AI models, not executing financial tasks itself.

financial-modeling market-analysis investment-research quantitative-finance financial-AI-evaluation
No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

44

Forks

4

Language

Python

License

Apache-2.0

Last pushed

Jan 08, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/HiThink-Research/MME-Finance"

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