MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

TL;DR

MM-Vet is a comprehensive benchmark designed to evaluate large multimodal models across complex tasks by assessing core vision-language capabilities and using an LLM-based evaluator for unified scoring.

Contribution

This paper introduces MM-Vet, a novel evaluation benchmark that systematically assesses multimodal models' integrated capabilities and proposes an LLM-based metric for versatile evaluation.

Findings

Different LMMs show varied strengths across core capabilities.

The LLM-based evaluator provides consistent scoring across question types.

Insights into model system paradigms and performance are obtained.

Abstract

We propose MM-Vet, an evaluation benchmark that examines large multimodal models (LMMs) on complicated multimodal tasks. Recent LMMs have shown various intriguing abilities, such as solving math problems written on the blackboard, reasoning about events and celebrities in news images, and explaining visual jokes. Rapid model advancements pose challenges to evaluation benchmark development. Problems include: (1) How to systematically structure and evaluate the complicated multimodal tasks; (2) How to design evaluation metrics that work well across question and answer types; and (3) How to give model insights beyond a simple performance ranking. To this end, we present MM-Vet, designed based on the insight that the intriguing ability to solve complicated tasks is often achieved by a generalist model being able to integrate different core vision-language (VL) capabilities. MM-Vet defines 6 core VL capabilities and examines the 16 integrations of interest derived from the capability combination. For evaluation metrics, we propose an LLM-based evaluator for open-ended outputs. The evaluator enables the evaluation across different question types and answer styles, resulting in a unified scoring metric. We evaluate representative LMMs on MM-Vet, providing insights into the capabilities of different LMM system paradigms and models.