Skip to main content
Model update · 2024 · preprint

Chai-1 entered the model lineage

Established Chai Discovery's first openly accessible complex-prediction model.

ModelChai-1 / Chai-2
OrganizationChai Discovery
Year2024
Event typeversion-release
Evidence sourcepreprint
Editorial statuscurated

Why this model matters

Chai-1 is a multi-modal biomolecular structure model on par with AlphaFold 3 for predicting proteins with ligands, nucleic acids and multimers. Chai Discovery (backed by OpenAI and Thrive) released it free for research and drug discovery, and followed with Chai-2 for zero-shot antibody design.

Current evidence boundary

  • Performance depends on the evaluation dataset and operating conditions.
  • Task-specific benchmark results should not be compared across unlike domains.
  • Outputs require task-specific scientific and experimental validation.