HiThink-Research/BizFinBench

A Business-Driven Real-World Financial Benchmark for Evaluating LLMs

32
/ 100
Emerging

BizFinBench helps financial professionals assess how well large language models (LLMs) understand and reason about complex financial data and scenarios. It provides over 100,000 real-world financial questions in English and Chinese, spanning tasks like anomaly attribution, numerical computations, and stock price predictions. Financial analysts, quantitative researchers, or risk managers can use this to evaluate and compare LLMs for their specific financial applications.

211 stars.

Use this if you need to rigorously test and benchmark an LLM's capability to perform financial tasks, understand market trends, or process financial reports.

Not ideal if you are looking for a general-purpose LLM benchmark not specifically focused on the nuances and precision required for financial applications.

financial-analysis market-intelligence risk-management quantitative-finance financial-forecasting
No License No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 7 / 25
Community 9 / 25

How are scores calculated?

Stars

211

Forks

10

Language

Python

License

Last pushed

Jan 09, 2026

Commits (30d)

0

Get this data via API

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

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