S1-Omni is a unified multimodal reasoning model aimed at advancing scientific understanding, prediction, and generation. While AI for Science (AI4S) has made significant strides through domain-specific models, tool-augmented LLMs, and scientific language models, the capabilities of these models remain highly fragmented, limiting the joint modeling of heterogeneous data, scientific laws, and expert knowledge. S1-Omni addresses this gap by consolidating these capabilities into a single, coherent scientific reasoning model.
The architecture of S1-Omni is built upon three core components: unified representation of scientific data, natural-world knowledge alignment, and decoding for domain-specific tasks.
First, S1-Omni maps natural-language instructions and scientific objects, including CIF, SMILES, protein sequences, spectra, and scientific images, into a shared representation space. Second, it incorporates scientific laws and expert knowledge into data construction and training, enabling the model to reason from scientific evidence. Third, it performs task-specific decoding to support a broad range of applications, including property prediction, spectrum-to-molecule generation, protein site and structure prediction, and scientific image generation and editing.
S1-Omni is trained on S1-Omni-Corpus, which covers 200 scientific tasks and contains millions of reasoning samples, and is evaluated on over 60 scientific benchmarks. It outperforms GPT-5.5 and Gemini-3.1-Pro on most benchmarks and matches or surpasses domain-specific models on several benchmarks. Overall, S1-Omni provides a practical path toward unified scientific modeling.
Blogger's Review: The introduction of S1-Omni marks a significant advancement in scientific reasoning models, with its multimodal capabilities offering a fresh perspective on scientific research. By unifying different types of data and knowledge, S1-Omni not only improves the accuracy of reasoning but also paves the way for future scientific exploration. Its outstanding performance across multiple benchmarks demonstrates its potential in practical applications.