OmniEvalKit: A Modular, Lightweight Toolbox for Evaluating Large Language Model and its Omni-Extensions

TL;DR

OmniEvalKit is a modular, lightweight benchmarking toolbox that enables comprehensive evaluation of large language models and their omni-extensions across multilingual, multidomain, and multimodal tasks, supporting over 100 models and 50 datasets.

Contribution

It introduces a novel, flexible, and fast-deployable evaluation framework that integrates diverse models and datasets seamlessly, enhancing LLM assessment capabilities.

Findings

Supports over 100 LLMs and 50 datasets

Enables evaluation across multiple capabilities simultaneously

Provides a lightweight, automated evaluation system

Abstract

The rapid advancements in Large Language Models (LLMs) have significantly expanded their applications, ranging from multilingual support to domain-specific tasks and multimodal integration. In this paper, we present OmniEvalKit, a novel benchmarking toolbox designed to evaluate LLMs and their omni-extensions across multilingual, multidomain, and multimodal capabilities. Unlike existing benchmarks that often focus on a single aspect, OmniEvalKit provides a modular, lightweight, and automated evaluation system. It is structured with a modular architecture comprising a Static Builder and Dynamic Data Flow, promoting the seamless integration of new models and datasets. OmniEvalKit supports over 100 LLMs and 50 evaluation datasets, covering comprehensive evaluations across thousands of model-dataset combinations. OmniEvalKit is dedicated to creating an ultra-lightweight and fast-deployable evaluation framework, making downstream applications more convenient and versatile for the AI community.