PhysicalAI.bestOur standard
Vision-language-action

OpenVLA

OpenVLA is a research VLA with public weights and adaptation tooling, connecting visual observations and language instructions to manipulation actions.

Source contextPrimary specReviewed
Sources 2
openvla/openvla official repository

openvla · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

OpenVLA research project

OpenVLA research team · Publication date not disclosed · Source accessed 2026-09-28

Reviewed recordLast reviewed 3 sources ↗4 sourced fields
Official source Suggest a correction

Architecture and scope

Fine-tuning options include low-rank adaptation and full training. The repository names RLDS data pipelines and Open X-Embodiment mixtures; local task data and action normalization remain necessary integration work.

Source contextPrimary specReviewed
Sources 2
openvla/openvla official repository

openvla · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

OpenVLA research project

OpenVLA research team · Publication date not disclosed · Source accessed 2026-09-28

Integration and evaluation

BridgeData and LIBERO evaluation paths are documented. Scores must retain the checkpoint and benchmark protocol; the separately released OFT implementation changes training and inference.

Source contextPrimary specReviewed
Sources 2
openvla/openvla official repository

openvla · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

OpenVLA research project

OpenVLA research team · Publication date not disclosed · Source accessed 2026-09-28

Evidence boundary

Model family weights are not a tested controller for every manipulator.

Source contextPrimary specReviewed
Sources 2
openvla/openvla official repository

openvla · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

OpenVLA research project

OpenVLA research team · Publication date not disclosed · Source accessed 2026-09-28

Model identity

Developer
OpenVLA research team
Primary specReviewed
Sources 1
openvla/openvla official repository

openvla · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Exact version / scope
OpenVLA 7B
Primary specReviewed
Sources 1
openvla/openvla official repository

openvla · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Category
Vision-language-action
Primary specReviewed
Sources 1
openvla/openvla official repository

openvla · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Access model
Public training code and pretrained checkpoint
Primary specReviewed
Sources 1
openvla/openvla official repository

openvla · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

License
Not publicly disclosed

Inputs, outputs & embodiment

Inputs
Not publicly disclosed
Outputs
Not publicly disclosed
Embodiment
Not publicly disclosed

Implementation & training

Compute
Not publicly disclosed
Training-data disclosures
Not publicly disclosed
Integrations
Not publicly disclosed

Reported benchmark results

Context before scores. Results from different benchmarks are not directly comparable. A simulation result does not establish real-world reliability, safety or commercial availability.
No result meets our complete revision and methodology requirements for this record yet. Inspect the original benchmark documentation before comparing published scores.

What this evidence does not establish

  • Model family weights are not a tested controller for every manipulator.
  • Pricing and deployment service terms were not verified.

Relationships & deployments

modelOpenVLA-OFT ↗stackOpen X-Embodiment ↗stackBridgeData V2 ↗benchmarkLIBERO ↗

Related reading is an editorial crosslink. Sourced connections describe relationships reported in the cited material. A link to a versioned profile does not establish compatibility with that version unless the connection note explicitly identifies it.

uses
OpenVLA-OFT → OpenVLA
Sources 1
moojink/openvla-oft official repository

moojink · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Connection reviewed 2026-09-28

Curated comparisons

OpenVLA vs SmolVLA

Record history & verified changes

A research review records when we checked a source. It does not mark a product launch or a new deployment.

Initial reviewed record. No subsequent field change has been recorded.

Inspect the evidence

Sources & evidence

md-openvla-project
OpenVLA research project

OpenVLA research team · Paper · Publication date not disclosed · Source accessed 2026-09-28

Factual summary and attribution only; no upstream prose, images, weights, or dataset redistributed.

Referenced by 1 record: OpenVLA