Evaluating the Effectiveness of Cost-Efficient Large Language Models in Benchmark Biomedical Tasks

TL;DR

This study evaluates various cost-efficient Large Language Models across multiple biomedical tasks, revealing no single model excels universally but different models perform best in specific applications, guiding optimal model selection.

Contribution

It provides a comprehensive comparison of open-source and closed-source LLMs for biomedical tasks, highlighting their strengths and trade-offs.

Findings

No single LLM outperforms others across all tasks

Open-source LLMs can match or surpass closed-source models in performance

Open-source models offer faster inference and better privacy

Abstract

This paper presents a comprehensive evaluation of cost-efficient Large Language Models (LLMs) for diverse biomedical tasks spanning both text and image modalities. We evaluated a range of closed-source and open-source LLMs on tasks such as biomedical text classification and generation, question answering, and multimodal image processing. Our experimental findings indicate that there is no single LLM that can consistently outperform others across all tasks. Instead, different LLMs excel in different tasks. While some closed-source LLMs demonstrate strong performance on specific tasks, their open-source counterparts achieve comparable results (sometimes even better), with additional benefits like faster inference and enhanced privacy. Our experimental results offer valuable insights for selecting models that are optimally suited for specific biomedical applications.