MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

TL;DR

This paper introduces MME, the first comprehensive benchmark for evaluating Multimodal Large Language Models, covering perception and cognition across 14 subtasks with manually designed annotations to ensure fair comparison and robust assessment.

Contribution

It presents a new evaluation benchmark for MLLMs with manually crafted instructions, enabling fair comparison and detailed analysis of model capabilities.

Findings

Existing MLLMs still have significant room for improvement.

The benchmark reveals potential directions for future model optimization.

30 advanced MLLMs were comprehensively evaluated.

Abstract

Multimodal Large Language Model (MLLM) relies on the powerful LLM to perform multimodal tasks, showing amazing emergent abilities in recent studies, such as writing poems based on an image. However, it is difficult for these case studies to fully reflect the performance of MLLM, lacking a comprehensive evaluation. In this paper, we fill in this blank, presenting the first comprehensive MLLM Evaluation benchmark MME. It measures both perception and cognition abilities on a total of 14 subtasks. In order to avoid data leakage that may arise from direct use of public datasets for evaluation, the annotations of instruction-answer pairs are all manually designed. The concise instruction design allows us to fairly compare MLLMs, instead of struggling in prompt engineering. Besides, with such an instruction, we can also easily carry out quantitative statistics. A total of 30 advanced MLLMs are comprehensively evaluated on our MME, which not only suggests that existing MLLMs still have a large room for improvement, but also reveals the potential directions for the subsequent model optimization. The data are released at the project page https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models/tree/Evaluation.