MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI
This provides a more extensive benchmark for evaluating LVLMs towards multitask AGI, addressing gaps in existing multimodal assessments, though it is incremental as it builds on prior benchmarking efforts.
The authors tackled the limited evaluation of Large Vision-Language Models (LVLMs) by introducing MMT-Bench, a comprehensive benchmark with 31,325 multi-choice visual questions across 32 meta-tasks and 162 subtasks, which revealed significant challenges for 30 tested LVLMs including GPT-4V and GeminiProVision.
Large Vision-Language Models (LVLMs) show significant strides in general-purpose multimodal applications such as visual dialogue and embodied navigation. However, existing multimodal evaluation benchmarks cover a limited number of multimodal tasks testing rudimentary capabilities, falling short in tracking LVLM development. In this study, we present MMT-Bench, a comprehensive benchmark designed to assess LVLMs across massive multimodal tasks requiring expert knowledge and deliberate visual recognition, localization, reasoning, and planning. MMT-Bench comprises $31,325$ meticulously curated multi-choice visual questions from various multimodal scenarios such as vehicle driving and embodied navigation, covering $32$ core meta-tasks and $162$ subtasks in multimodal understanding. Due to its extensive task coverage, MMT-Bench enables the evaluation of LVLMs using a task map, facilitating the discovery of in- and out-of-domain tasks. Evaluation results involving $30$ LVLMs such as the proprietary GPT-4V, GeminiProVision, and open-sourced InternVL-Chat, underscore the significant challenges posed by MMT-Bench. We anticipate that MMT-Bench will inspire the community to develop next-generation multimodal foundation models aimed at achieving general-purpose multimodal intelligence.