OmniBench: Towards The Future of Universal Omni-Language Models

Yizhi LI, Yinghao Ma, Ge Zhang, Ruibin Yuan, King Zhu, Hangyu Guo, Yiming Liang, Jiaheng Liu, Zekun Moore Wang, Jian Yang, Siwei Wu, Xingwei Qu, Jinjie Shi, Xinyue Zhang, Zhenzhu Yang, Yidan WEN, Yanghai Wang, Shihao Li, Zhaoxiang Zhang, Ruibo Liu et al. (3 additional authors not shown)

Keywords: Omni-models, MLLM, Foundation Model, LLM, OLM

TL;DR: A challenging tri-modal reasoning benchmark for evaluating omni-language models.

Abstract:

Recent advancements in multimodal large language models (MLLMs) have aimed to integrate and interpret data across diverse modalities. However, the capacity of these models to concurrently process and reason about multiple modalities remains underexplored, partly due to the lack of comprehensive modality-wise benchmarks.
We introduce **OmniBench**, a novel benchmark designed to rigorously evaluate models' ability to recognize, interpret, and reason across **visual**, **acoustic**, and **textual** inputs simultaneously. We define language models capable of such tri-modal processing as the omni-language models (OLMs).
OmniBench is distinguished by high-quality human annotations, ensuring that accurate responses require integrated understanding and reasoning across all three modalities. Our main findings reveal that:
_i)_ open-source OLMs exhibit critical limitations in instruction-following and reasoning capabilities within tri-modal contexts; and _ii)_ most baselines models perform poorly (below 50% accuracy) even when provided with alternative textual representations of images or/and audio.
These results suggest that the ability to construct a consistent context from text, image, and audio is often overlooked in existing MLLM training paradigms.
To address this gap, we curate an instruction tuning dataset of 84.5K training samples, **OmniInstruct**, for training OLMs to adapt to tri-modal contexts.
We advocate for future research to focus on developing more robust tri-modal integration techniques and training strategies to enhance OLMs.
Codes, data and live leaderboard could be found at https://m-a-p.ai/OmniBench.

Dataset URL: https://huggingface.co/datasets/m-a-p/OmniBench

Code URL: https://github.com/multimodal-art-projection/OmniBench

Primary Area: Datasets & Benchmarks for applications in language modeling and vision language modeling

Submission Number: 1648