All Competitors

Every biological foundation model, evaluated and ranked by the bio.rodeo team

Applications

Architectures

Learning Paradigms

Biological Subjects

Showing 1–13 of 13 filtered models

DNA & Gene

AlphaGenome

Google DeepMind

Google DeepMind model that predicts thousands of functional genomic tracks at single base-pair resolution from megabase-scale DNA sequences.

1.9K50
See the scorecard
DNA & Gene

Evo 2

Arc Institute

Genomic foundation model trained on 9.3 trillion DNA base pairs spanning all domains of life, with 40B parameters and a 1-million-token context window.

3.8K227
See the scorecard
DNA & Gene

Evo

Arc Institute

A 7B parameter genomic foundation model using StripedHyena architecture to model prokaryotic DNA, RNA, and proteins at single-nucleotide resolution with 131k token context.

1.5K1958.1K
See the scorecard
DNA & Gene

gLM

Harvard University / MIT

Genomic language model trained on metagenomic scaffolds that learns protein co-regulation and function by modeling gene context and operon structure.

8881
See the scorecard
DNA & Gene

Caduceus

Kuleshov Lab

Bidirectional, reverse-complement equivariant DNA language models built on Mamba SSMs. Outperforms models 10x larger on long-range variant effect prediction.

232
See the scorecard
DNA & Gene

GPN

Song Lab

A DNA language model for unsupervised genome-wide variant effect prediction, trained on multispecies genomes via masked language modeling without functional annotation labels.

339
See the scorecard
DNA & Gene

GPN-MSA

UC Berkeley

Transformer-based DNA language model using whole-genome multispecies alignments for genome-wide variant effect prediction across coding and non-coding regions.

33965
See the scorecard
DNA & Gene

HyenaDNA

HazyResearch

Genomic foundation model using the Hyena operator to process DNA at single-nucleotide resolution with context lengths up to 1 million tokens, 500x longer than transformer-based predecessors.

778460
See the scorecard
DNA & Gene

DNABERT-2

MAGICS Lab

Multi-species genomic foundation model replacing k-mer tokenization with BPE, achieving state-of-the-art performance with 21x fewer parameters than prior leading models.

47837595.5K
See the scorecard
DNA & Gene

GENA-LM

AIRI Institute

A family of transformer-based DNA language models supporting context lengths up to 36,000 bp via BPE tokenization and BigBird sparse attention.

221
See the scorecard
DNA & Gene

Nucleotide Transformer

InstaDeep

A family of DNA foundation models (500M–2.5B parameters) trained on 3,200+ human genomes and 850 species for genomic sequence understanding and variant effect prediction.

858173
See the scorecard
DNA & Gene

MoDNA

University of Texas at Arlington

Motif-oriented DNA pre-training framework using an ELECTRA-style generator-discriminator architecture to learn biologically informed genomic representations.

25
See the scorecard
DNA & Gene

DNABERT

Northwestern University

BERT-based pre-trained model for DNA sequences using k-mer tokenization. Achieves state-of-the-art performance on promoter, splice site, and transcription factor binding prediction.

74918.7K
See the scorecard