# VisFinEval: A Scenario-Driven Chinese Multimodal Benchmark for Holistic Financial Understanding

arXiv: https://arxiv.org/abs/2508.09641 · HTML: https://mlsanity.com/paper/2508.09641/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Aug 2025.

## Built on by (most cited first, 6 of 6)

- [Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows](https://mlsanity.com/paper/2512.13168/) (2025)
- [FCMBench: The First Large-scale Financial Credit Multimodal Benchmark for Real-world Applications](https://mlsanity.com/paper/2601.00150/) (2026)
- [BizFinBench.v2: Towards Reliable LLMs in Finance via Real-User Data and Offline/Online Bilingual Evaluation](https://mlsanity.com/paper/2601.06401/) (2026)
- [UniFinEval: Towards Unified Evaluation of Financial Multimodal Models across Text, Images and Videos](https://mlsanity.com/paper/2601.22162/) (2026)
- [Captioning Daily Activity Images in Early Childhood Education: Benchmark and Algorithm](https://mlsanity.com/paper/2604.01941/) (2026)
- [Benchmarking Large Vision-Language Models on CFMME: A Comprehensive Chinese Financial Multimodal Evaluation Dataset](https://mlsanity.com/paper/2605.29462/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) hold great promise for automating complex financial analysis. To comprehensively evaluate their capabilities, we introduce VisFinEval, the first large-scale Chinese benchmark that spans the full front-middle-back office lifecycle of financial tasks. VisFinEval comprises 15,848 annotated question-answer pairs drawn from eight common financial image modalities (e.g., K-line charts, financial statements, official seals), organized into three hierarchical scenario depths: Financial Knowledge & Data Analysis, Financial Analysis & Decision Support, and Financial Risk Control & Asset Optimization. We evaluate 21 state-of-the-art MLLMs in a zero-shot setting. The top model, Qwen-VL-max, achieves an overall accuracy of 76.3%, outperforming non-expert humans but trailing financial experts by over 14 percentage points. Our error analysis uncovers six recurring failure modes-including cross-modal misalignment, hallucinations, and lapses in business-process reasoning-that highlight critical avenues for future research. VisFinEval aims to accelerate the development of robust, domain-tailored MLLMs capable of seamlessly integrating textual and visual financial information. The data and the code are available at https://github.com/SUFE-AIFLM-Lab/VisFinEval.