Project AURIONAI Use-Cases Research & Innovation
robot policy

Helix

Figure AI VLA for its own robots, trained on about 500 h of teleoperation data.

Figure AIFigure AIUSAHelixFamily
Figure AI
Levelmodel
Classrobot policy
Parameters7.08B
Contextnot in the notes
Released20 Feb 2025
Opennessproprietary
Runs onnot in the notes
Statusactive

Lineage

successor
Helix 02 to Helix 2.5: successor, medium confidenceHelix to Helix 02: successor, high confidenceHelixHelixFigure AI, Feb 2025Helix 02Helix 02Figure AI, Jan 2026Helix 2.5Helix 2.5Figure AI, Sep 2026
Figure AIHelix 02 is a child (successor)high confidencenotes
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 3 models. Confidence and evidence are the notes' own.

Industry Use Cases

Industrial
Humanoid parts handling in automotive manufacturing

R&D Topics

Vision-language-action robot policiesproduced by

Identity

Developer
Figure AI
Family
Helix
Released
20 Feb 2025 sourcessecondary report
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
hybrid System 2: 7B open-weight VLM at 7 to 9 Hz; System 1: 80M visuomotor policy at 200 Hz; 35-DoF upper body
Total parameters
7.08B sources
Active parameters
–
Checkpoint parameters
–
Note
7B + 80M
Context length
not in the notes
Input
image, text
Output
action
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
proprietary
Licence
Proprietary sources
Access routes
internal only
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Sources

  1. aiwiki.ai/wiki/helix_vla https://aiwiki.ai/wiki/helix_vla

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Helix", https://aurion.semai.id/models/figure-ai-helix/, records of October 2026.