Multimodal Large Language Models (MLLMs) process visual, acoustic, and textual inputs, addressing the limitations of single-modality LLMs. However, existing benchmarks often overlook tri-modal evaluation in Traditional Chinese and do not consider inference latency. To address this, we introduce Multi-TW, the first Traditional Chinese benchmark for evaluating the performance and latency of any-to-any multimodal models. Multi-TW includes 900 multiple-choice questions (image and text, audio and text pairs) sourced from official proficiency tests developed with the Steering Committee for the Test of Proficiency-Huayu (SC-TOP). We evaluated various any-to-any models and vision-language models (VLMs) with audio transcription. Our results show that closed-source models generally outperform open-source ones across modalities, although open-source models can perform well in audio tasks. End-to-end any-to-any pipelines offer clear latency advantages compared to VLMs using separate audio transcription. Multi-TW presents a comprehensive view of model capabilities and highlights the need for Traditional Chinese fine-tuning and efficient multimodal architectures.
@article{arxiv.2508.01274,
title = {Multi-TW: Benchmarking Multimodal Models on Traditional Chinese Question Answering in Taiwan},
author = {Jui-Ming Yao and Bing-Cheng Xie and Sheng-Wei Peng and Hao-Yuan Chen and He-Rong Zheng and Bing-Jia Tan and Peter Shaojui Wang and Shun-Feng Su},
journal= {arXiv preprint arXiv:2508.01274},
year = {2025}
}