MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application
This addresses the problem of inadequate evaluation for financial AI applications that involve diverse languages and data types, though it is incremental as it builds on existing benchmarking efforts by adding new dimensions.
The authors tackled the lack of realistic multilingual and multimodal benchmarks for evaluating large language models in finance by introducing MultiFinBen, an expert-annotated benchmark across five languages and three modalities, and found that even top models like GPT-4o achieved only 46.01% overall accuracy, with sharp drops in multilingual tasks.
Real-world financial analysis involves information across multiple languages and modalities, from reports and news to scanned filings and meeting recordings. Yet most existing evaluations of LLMs in finance remain text-only, monolingual, and largely saturated by current models. To bridge these gaps, we present MultiFinBen, the first expert-annotated multilingual (five languages) and multimodal (text, vision, audio) benchmark for evaluating LLMs in realistic financial contexts. MultiFinBen introduces two new task families: multilingual financial reasoning, which tests cross-lingual evidence integration from filings and news, and financial OCR, which extracts structured text from scanned documents containing tables and charts. Rather than aggregating all available datasets, we apply a structured, difficulty-aware selection based on advanced model performance, ensuring balanced challenge and removing redundant tasks. Evaluating 21 leading LLMs shows that even frontier multimodal models like GPT-4o achieve only 46.01% overall, stronger on vision and audio but dropping sharply in multilingual settings. These findings expose persistent limitations in multilingual, multimodal, and expert-level financial reasoning. All datasets, evaluation scripts, and leaderboards are publicly released.