Octo
Octo Model Team
Open-source generalist robot policy pretrained on Open X-Embodiment trajectories and designed for fine-tuning to new robots and tasks.
- Code
- Not listed
- Weights
- Available
- Checkpoint
- Available
- License
- mit
Decision summary
Fine-tuning to new observation spaces
Hardware, latency, dependencies, and checkpoint loading are not pipeline-tested.
Verify weight files, sizes, format, and loading instructions.
Release history
Source-backed release timing for this canonical model record.
- Paper
Model series introduced
Release timing is anchored to the cited paper publication date.
Selection readiness
Evidence dimensions for deciding whether this model is ready to inspect, compare, or adopt. Scores describe catalog evidence, not task performance.
Published evaluation
How scores work71/100
Useful
5/6 dimensions scored · 51% confidence
Engineering checks (OBRS) behind this record
Needs Audit
OBRS metadata and reported test evidence. A breakdown behind Selection readiness, not a separate score or an independent OpenBot certification.
- A passing real-hardware test report is required.
- A passing ingestion/pipeline test report is required.
- A passing privacy and provenance review is required.
Why these scores
The strongest decision reasons behind Selection readiness.
Artifact availability
UsefulArtifact availability is declared by the published record; exact files and loadability still require metadata verification.
Training and loading reproducibility
UsefulConfiguration files are present; runtime loading is not tested.
Evaluation evidence
UnknownNo structured evaluation evidence has been verified.
Data requirements
Declared loop-data needs, missing evidence, and the next checks that matter.
Observation / ego video
observation · goal image
Language intent / task phase
language intent · goal image
Action / robot state
actions · robot state
Sim-real / embodiment metadata
robot state
Critical gaps
Core categories are represented. Interface alignment and data quality still require verification.
Linked datasets
Signal-level links only. Verify runtime interfaces before use.
EgoWorld
Schema validation for LeRobot v3
provisional fit 83 · confidence 40
2 matched · 1 unknown
Egocentric Adjust Bottle
LeRobot conversion tests
provisional fit 100 · confidence 60
3 matched · 0 unknown
EgoStation GoPro Pick-and-Place
Pick-and-place benchmark fixtures
provisional fit 100 · confidence 60
3 matched · 0 unknown
More evidenceShowHide
Additional decision dimensions
Access and license are declared by the source.
75 · c85Required signal categories are structured; exact tensor and action interfaces still need verification.
76 · c70Hardware, latency, dependencies, and checkpoint loading are not pipeline-tested.
70 · c55Artifact facts
- release_year
- official_claim
- 2024
- curated official source year
- model.required_signals
- official_claim
- observation · actions · robot state · language intent · goal image
- Official model documentation and curated signal mapping
- model.hub
- official_claim
- declared
- curated model hub link
- model.config_files
- metadata_verified
- repository: rail-berkeley/octo-small-1.5 · count: 1 · sample files: config.json
- Hugging Face model metadata siblings
- license.weights
- metadata_verified
- mit
- Hugging Face model card license metadata
- license
- metadata_verified
- mit
- Hugging Face model card license metadata
- release_timing
- metadata_verified
- 2024-05-20T17:57:01.000Z
- arXiv 2405.12213 published
- discovery.source
- secondary_claim
- name: worldbench/awesome-embodied-data-pyramid · trust: discovery_only · revision: 0568599d0619f20946e8089f6a941d0d9e30b690
- #table-embodied-foundation-models-vla-wam, table 17, row 3
- discovery.raw_fields
- secondary_claim
- Time: 2024.5 · Method: Octo · Institution: UC Berkeley · Project: [](https://octo-models.github.io/) · Model: VLA · Data: ![Real][data-real]
- #table-embodied-foundation-models-vla-wam, table 17, row 3
- model.reported_release_time
- secondary_claim
- 2024.5
- #table-embodied-foundation-models-vla-wam, table 17, row 3
- model.type
- secondary_claim
- VLA
- #table-embodied-foundation-models-vla-wam, table 17, row 3
- model.training_data_layers
- secondary_claim
- real_robot
- #table-embodied-foundation-models-vla-wam, table 17, row 3
- model.institution
- secondary_claim
- UC Berkeley
- #table-embodied-foundation-models-vla-wam, table 17, row 3
- catalog.curation
- secondary_claim
- tier: editorial_focus · collection: WorldBench Awesome Embodied Data Pyramid · policy: human_curated_priority
- #table-embodied-foundation-models-vla-wam, table 17, row 3
Additional references
OpenBot notes
- Good bridge between pure policy learning and broader VLA/WAM framing.
- OpenBot can help decide whether a dataset has enough action/state structure for Octo-style fine-tuning.