FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models

Xin Guo, Haotian Xia, Zhaowei Liu, Hanyang Cao, Zhi Yang +12 more
8/19/2023
cs.CL

No official code found. Best implementation: microsoftarchive/promptbench (2,816 stars, MIT, last commit 2026-02-20). 1 more below.

Abstract

Large language models have demonstrated outstanding performance in various natural language processing tasks, but their security capabilities in the financial domain have not been explored, and their performance on complex tasks like financial agent remains unknown. This paper presents FinEval, a benchmark designed to evaluate LLMs' financial domain knowledge and practical abilities. The dataset contains 8,351 questions categorized into four different key areas: Financial Academic Knowledge, Financial Industry Knowledge, Financial Security Knowledge, and Financial Agent. Financial Academic Knowledge comprises 4,661 multiple-choice questions spanning 34 subjects such as finance and economics. Financial Industry Knowledge contains 1,434 questions covering practical scenarios like investment research. Financial Security Knowledge assesses models through 1,640 questions on topics like application security and cryptography. Financial Agent evaluates tool usage and complex reasoning with 616 questions. FinEval has multiple evaluation settings, including zero-shot, five-shot with chain-of-thought, and assesses model performance using objective and subjective criteria. Our results show that Claude 3.5-Sonnet achieves the highest weighted average score of 72.9 across all financial domain categories under zero-shot setting. Our work provides a comprehensive benchmark closely aligned with Chinese financial domain.

View on arXivView PDF

Code Implementations(2)

SUFE-AIFLM-Lab/FinEvalCommunity100%
Apache-2.0

The FinEval financial domain evaluation benchmark, based on quantitative fundamental methods and developed through long-term objective research, summarization, and rigorous manual screening, utilizes over 26,000 diverse question types that are highly consistent with real-world application scenarios.

28622CSS, HTMLAug 13, 20231 years agoApache-2.0
microsoftarchive/promptbenchCommunity72%
MIT

A unified evaluation framework for large language models

2,816221PythonJun 13, 20238 months agoMIT
adversarial-attacksbenchmarkchatgptevaluationlarge-language-models+3 more

Similar Papers

FinMCP-Bench: Benchmarking LLM Agents for Real-World Financial Tool Use under the Model Context Protocol

91% match2026

PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance

90% match1 repo8862023

CFBenchmark: Chinese Financial Assistant Benchmark for Large Language Model

89% match1 repo572023

Evaluating Financial Intelligence in Large Language Models: Benchmarking SuperInvesting AI with LLM Engines

89% match2026

BizBench: A Quantitative Reasoning Benchmark for Business and Finance

89% match2023

Large Language Models in Finance: A Survey

89% match2023

Cite this paper

@article{guo2023fineval,
  title  = {FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models},
  author = {Xin Guo and Haotian Xia and Zhaowei Liu and Hanyang Cao and Zhi Yang and Zhiqiang Liu and Sizhe Wang and Jinyi Niu and Chuqi Wang and Yanhui Wang and Xiaolong Liang and Xiaoming Huang and Bing Zhu and Zhongyu Wei and Yun Chen and Weining Shen and Liwen Zhang},
  year   = {2023},
  eprint = {2308.09975},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2308.09975v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2308.09975.svg)](https://codeofpaper.com/paper/2308.09975)

Discussion