All Competitors

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

Showing 124 of 61 filtered models

Protein

RFdiffusion3

Institute for Protein Design

All-atom diffusion model for de novo protein design conditioned on ligands, nucleic acids, and arbitrary non-protein atoms, enabling enzyme and DNA binder design.

79128
See the scorecard
Protein

RFdiffusion2

Institute for Protein Design

Atom-level generative diffusion model for de novo enzyme design. Scaffolds arbitrary functional group geometries, solving all 41 benchmark active sites vs. 16/41 for prior methods.

41672
See the scorecard
Protein

Boltz-2

MIT CSAIL / Recursion Pharmaceuticals

Open model that jointly predicts biomolecular structure and small-molecule binding affinity, approaching FEP+ accuracy in seconds on a single GPU.

3.9K285
See the scorecard
Protein

Pinal

Westlake University

A 16B-parameter framework for de novo protein design from natural language, converting text descriptions into functional protein sequences via two-stage structure-conditioned generation.

9321
See the scorecard
Protein

LigandMPNN

Institute for Protein Design

Protein sequence design method that explicitly models small molecules, nucleotides, and metals at atomic resolution, enabling ligand-aware design with 100+ validated designs.

567183
See the scorecard
Protein

Protenix

ByteDance AI Lab

Open-source PyTorch reproduction of AlphaFold 3 (Apache 2.0) that matches or exceeds AF3 performance on protein-ligand, protein-protein, and protein-nucleic acid benchmarks.

1.8K120
See the scorecard
Protein

Evolla

Westlake University

An 80B-parameter multimodal protein-language model that decodes protein function through natural language dialogue, integrating sequence, structure, and evolutionary context.

671941
See the scorecard
Protein

ProteinDT

UC Berkeley

A multimodal framework for text-guided protein design, enabling sequence generation, zero-shot editing, and property prediction via contrastive learning.

10696
See the scorecard
Protein

BioEmu-1

Microsoft

Generative deep learning model from Microsoft Research that emulates protein equilibrium ensembles at 100,000x the speed of molecular dynamics simulation.

794246
See the scorecard
Protein

ESM Cambrian

EvolutionaryScale

A family of protein language models (300M, 600M, 6B parameters) for representation learning that substantially outperforms ESM-2 at equivalent or smaller scale.

2.3K9.4K
See the scorecard
Protein

Boltz-1

MIT

Open-source deep learning model for biomolecular structure prediction achieving AlphaFold3-level accuracy, trained entirely on publicly available data.

3.9K313
See the scorecard
Protein

SFM-Protein

Microsoft Research

A transformer protein language model using integrative co-evolutionary pre-training to capture both short-range and long-range residue interactions from sequence alone.

3
See the scorecard
Protein

Chai-1

Chai Discovery

Multi-modal foundation model for biomolecular structure prediction covering proteins, small molecules, DNA, RNA, and glycans in a unified diffusion framework.

1.9K301
See the scorecard
Protein

ProteinBench

ByteDance Research

A holistic evaluation framework for protein foundation models, assessing 25+ models across 8 tasks using four-dimensional metrics: quality, novelty, diversity, and robustness.

19
See the scorecard
Protein

HelixFold3

Baidu PaddleHelix

Open-source reproduction of AlphaFold 3 from Baidu PaddleHelix, predicting structures of proteins, nucleic acids, and small molecule ligands with comparable accuracy.

1.1K30
See the scorecard
Protein

SPIRED-Fitness

Tsinghua University

End-to-end framework predicting protein structure and mutational fitness from a single sequence, with 5x faster inference than ESMFold at comparable accuracy.

5032
See the scorecard
Protein

ESM-3

EvolutionaryScale

Multimodal generative protein language model that jointly reasons over sequence, structure, and function. Trained at 98B parameters on 2.78 billion proteins.

2.3K2474K
See the scorecard
Protein

Compute-Optimal PLM

BioMap

Scaling law study for protein language models that identifies compute-optimal training regimes for CLM and MLM architectures using 939M protein sequences.

1134
See the scorecard
Protein

Prot2Token

University of Missouri

A unified multi-task framework that converts diverse protein prediction tasks into autoregressive next-token prediction using pre-trained protein language model encoders.

3810
See the scorecard
Protein

ProTrek

Westlake University

Tri-modal protein language model unifying sequence, structure, and function via contrastive learning, enabling natural-language protein search across billions of entries.

2041444
See the scorecard
Protein

OpenFold

Aqlaboratory

A trainable, open-source reimplementation of AlphaFold2 that matches its accuracy and runs 3-5x faster, enabling mechanistic research into protein structure learning.

3.3K382
See the scorecard
Protein

AlphaFold 3

Google DeepMind

Unified diffusion-based model predicting structures of protein complexes with nucleic acids, small molecules, ions, and modified residues with atomic accuracy.

7.9K10.1K
See the scorecard
Protein

PLMSearch

Fudan University

Protein language model-based sequence search that detects remote homologs with threefold higher sensitivity than MMseqs2 at comparable speed.

7967
See the scorecard
Protein

RoseTTAFold All-Atom

Baker Lab

Deep network that predicts structures of full biological assemblies containing proteins, nucleic acids, small molecules, metals, and covalent modifications simultaneously.

802810
See the scorecard