OmniBench Music
Music component of OmniBench, a comprehensive benchmark for evaluating omni-language models' ability to recognize, interpret, and reason across visual, acoustic, and textual inputs simultaneously. The music category includes various compositions and performances that require integrated understanding across text, image, and audio modalities.
Qwen2.5-Omni-7B from Alibaba Cloud / Qwen Team currently leads the OmniBench Music leaderboard with a score of 0.528 across 1 evaluated AI models.
What OmniBench Music measures
OmniBench Music is a multimodal benchmark that evaluates large language models on multimodal and audio tasks. LLM Stats tracks 1 model on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.5, with the leader reaching 0.5.
Compare leaders on the best AI for multimodal and best AI for audio leaderboards.
Publication
- Paper
- OmniBench: Towards The Future of Universal Omni-Language Models
- Authors
- Yizhi Li, Yinghao Ma, Ge Zhang, Ruibin Yuan, and 19 others
- Published
- arXiv
- 2409.15272
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.
Qwen2.5-Omni-7B leads with 52.8%.
Progress Over Time
Interactive timeline showing model performance evolution on OmniBench Music
OmniBench Music Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Alibaba Cloud / Qwen Team | 7B | — | — |
FAQ
Common questions about OmniBench Music.
More evaluations to explore
Related benchmarks in the same category
MMMU (Massive Multi-discipline Multimodal Understanding) is a benchmark designed to evaluate multimodal models on college-level subject knowledge and deliberate reasoning. Contains 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering across 30 subjects and 183 subfields.
A more robust multi-discipline multimodal understanding benchmark that enhances MMMU through a three-step process: filtering text-only answerable questions, augmenting candidate options, and introducing vision-only input settings. Achieves significantly lower model performance (16.8-26.9%) compared to original MMMU, providing more rigorous evaluation that closely mimics real-world scenarios.
CharXiv-R is the reasoning component of the CharXiv benchmark, focusing on complex reasoning questions that require synthesizing information across visual chart elements. It evaluates multimodal large language models on their ability to understand and reason about scientific charts from arXiv papers through various reasoning tasks.
MathVista evaluates mathematical reasoning of foundation models in visual contexts. It consists of 6,141 examples derived from 28 existing multimodal datasets and 3 newly created datasets (IQTest, FunctionQA, and PaperQA), combining challenges from diverse mathematical and visual tasks to assess models' ability to understand complex figures and perform rigorous reasoning.
AI2D is a dataset of 4,903 illustrative diagrams from grade school natural sciences (such as food webs, human physiology, and life cycles) with over 15,000 multiple choice questions and answers. The benchmark evaluates diagram understanding and visual reasoning capabilities, requiring models to interpret diagrammatic elements, relationships, and structure to answer questions about scientific concepts represented in visual form.
MATH-Vision is a dataset designed to measure multimodal mathematical reasoning capabilities. It focuses on evaluating how well models can solve mathematical problems that require both visual understanding and mathematical reasoning, bridging the gap between visual and mathematical domains.