Search papers, labs, and topics across Lattice.
This paper introduces OmniPhys, a comprehensive multimodal benchmark designed to enhance the capabilities of Multimodal Large Language Models (MLLMs) in physics understanding and generation, utilizing a dataset derived from Chinese educational materials. The benchmark includes 15,246 questions and 19,850 images, allowing for detailed analysis of reasoning processes and knowledge application in physics contexts. Evaluation results highlight significant deficiencies in current MLLMs, particularly in complex reasoning and visual generation tasks, underscoring the necessity of OmniPhys for advancing multimodal intelligence in scientific domains.
Current MLLMs struggle with complex physics reasoning, revealing critical gaps that OmniPhys aims to address with its extensive multimodal dataset.
Multimodal Large Language Models (MLLMs) have demonstrated strong abilities in solving diverse visual and textual reasoning tasks. However, their development in the physics domain is significantly hindered by the lack of a comprehensive benchmark. To fill this gap, we introduce OmniPhys, a large-scale benchmark for multimodal physics understanding and reasoning, covering middle school through university-level problems from Chinese Educational Corpora. OmniPhys consists of 15,246 questions and 19,850 images, accompanied by detailed annotations that support fine-grained analysis of reasoning processes and knowledge usage. Beyond conventional evaluation, OmniPhys is a benchmark that systematically evaluates multimodal outputs in the physics domain, including models'ability to generate structured physics diagrams, which constitute a fundamental component of authentic physics problem solving. Extensive evaluations reveal critical gaps in the capabilities of current MLLMs, especially in complex reasoning and visual generation. To address this, we release OmniPhys to serve as a foundational resource for advancing multimodal intelligence in physics and scientific domains. Codes and data are available at https://github.com/ECNU-RAIL/OmniPhys-EMNLP2026.
