BabelBench: An Omni Benchmark for Code-Driven Analysis of Multimodal and Multistructured Data

TL;DR

BabelBench is a comprehensive benchmark framework designed to evaluate large language models' abilities in handling multimodal, multistructured data with code execution, revealing significant room for improvement even in state-of-the-art models.

Contribution

This paper introduces BabelBench, a novel unified benchmark with 247 problems for assessing LLMs on multimodal, multistructured data processing and reasoning tasks.

Findings

ChatGPT-4 shows substantial room for improvement.

BabelBench covers perception, reasoning, and debugging tasks.

Provides guidance for future research in multimodal data handling.

Abstract

Large language models (LLMs) have become increasingly pivotal across various domains, especially in handling complex data types. This includes structured data processing, as exemplified by ChartQA and ChatGPT-Ada, and multimodal unstructured data processing as seen in Visual Question Answering (VQA). These areas have attracted significant attention from both industry and academia. Despite this, there remains a lack of unified evaluation methodologies for these diverse data handling scenarios. In response, we introduce BabelBench, an innovative benchmark framework that evaluates the proficiency of LLMs in managing multimodal multistructured data with code execution. BabelBench incorporates a dataset comprising 247 meticulously curated problems that challenge the models with tasks in perception, commonsense reasoning, logical reasoning, and so on. Besides the basic capabilities of multimodal understanding, structured data processing as well as code generation, these tasks demand advanced capabilities in exploration, planning, reasoning and debugging. Our experimental findings on BabelBench indicate that even cutting-edge models like ChatGPT 4 exhibit substantial room for improvement. The insights derived from our comprehensive analysis offer valuable guidance for future research within the community. The benchmark data can be found at https://github.com/FFD8FFE/babelbench.