All Competitors
Every biological foundation model, evaluated and ranked by the bio.rodeo team
Showing 1–8 of 8 filtered models
scLong
2310—Billion-parameter single-cell foundation model with self-attention over 28,000 human genes, adding Gene Ontology priors via a graph neural network.
Single-cell29OpennessRegFormer
———Single-cell foundation model combining regulatory network priors with a Mamba backbone for clustering, batch integration, and perturbation modeling.
Single-cell10OpennessscDiVa
—1—Renmin University of ChinaFebruary 3, 2026gene_expressioncell_type_annotationperturbation_prediction+6Single-cell foundation model built on masked discrete diffusion, jointly generating gene identities and expression values from 59 million cells.
Single-cell6OpennessKidney-specialized single-cell foundation model trained across four mammalian species for zero-shot cell-type annotation and batch integration.
Single-cellSpatial omics22OpennessscDMC
2——Single-cell foundation model with rank and expression-aware input streams, pairing masked gene modeling with cell-level contrastive learning.
Single-cell26OpennessGeneMamba
98813New Jersey Institute of TechnologyApril 22, 2025batch_integrationcell_type_annotationcontrastive_learning+2Single-cell foundation model built on bidirectional Mamba blocks and pretrained on 30 million cells for linear-time transcriptome embedding.
Single-cell67OpennessscContrast
34—Single-cell RNA-seq encoder trained with contrastive learning to merge plate- and droplet-based protocols, zero-shot on unseen tissues.
Single-cell39Openness