Helix 02
Robotics model
Price not published
Helix 2.5
PricePrice not published
Where it stands
1newer robotics model since its release
- Praxis-130 Sep 2026
- Before it from Figure AI
- Helix 0227 Jan 2026
- Weights
- Closed weights.
How to call it
Where to use Helix 2.5.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| None (runs only on Figure 03 robots; no public API, weights or waitlist) | figure.ai |
Pricing
Price not published.
No price source linked.
Specs
- Input
- Text, images and video
- Output
- Robot actions
- Context window
- Not published
- Max output
- Not published
- Open weights
- No
- Licence
- Proprietary
- Released
- 17 September 2026
- Status
- Current
- Type
- Robotics model
What stands out
What its maker marketed at launch, and what people found later, each with its source.
Zero-shot whole-body generalization to unseen homes
First
56% success (237/420 trials) tidying, towel folding and bed making in 30 never-seen Bay Area homes with no data from those homes; matched Helix 02’s success with half the adaptation data.
Pretrained from scratch on human video (Index)
Pretrained from random initialization on Figure’s Index human-video dataset (not a VLM); without it the same model scored 9%.
Human-to-robot transfer scaling law
First
Predictable scaling of robot performance with human-video data (forecast error 0.54% over an 8x data range).
Notes
‘first’ flags are Figure’s ‘to our knowledge’ claims (first zero-shot whole-body generalization at this scope; first human-to-robot transfer scaling law measured on a humanoid). Company-reported results. Architecture/parameter counts not disclosed.
Sources: Figure: Helix 2.5.