DYNA-2 (World-Action Model)
PricePrice not published
Where it stands
5newer robotics models since its release
- Praxis-130 Sep 2026
- Helix 2.517 Sep 2026
- UnifoLM-WLA-1.010 Sep 2026
- Skild S1 (Skild Brain)25 Aug 2026
- Generalist GEN-1.519 Aug 2026
- Weights
- Closed weights.
How to call it
Where to use DYNA-2 (World-Action Model).
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Dyna Robotics (commercial deployments) | dyna.co |
Pricing
Price not published.
No price source linked.
Specs
- Input
- Images, video and text
- Output
- Video and robot actions
- Context window
- Not published
- Max output
- Not published
- Open weights
- No
- Licence
- Proprietary
- Released
- 10 August 2026
- Status
- Current
- Type
- Robotics model
What stands out
What its maker marketed at launch, and what people found later, each with its source.
Human-to-robot scaling law
First
Pretrained on 1M+ hours of egocentric human video (~170 years); on-robot normalized score rose from 20% to 53% across 14 tasks as pretraining scaled from 1k to 1M hours. Dyna calls it the first scaling law demonstrated across the embodiment gap.
World-action model
One video-diffusion (mixture-of-transformers, flow matching) model that denoises future video and an action chunk jointly or separately; one-step distilled video generation 90x faster than the teacher.
Production quality gains
87% zero-shot customer-quality pass rate at a customer deployment vs 46% for DYNA-1; 1.55x more task completions than DYNA-1; bottle-cap opening learned with 10 minutes of robot data.
Notes
Predecessor DYNA-1 (2025) runs in production in hotels, restaurants and laundromats (towel folding etc.). No API or weights; adapts to arms, humanoid prototypes and dexterous hands with hours of local fine-tuning. Figure (Helix 2.5), Generalist (GEN-1) and Dyna all reported human-video scaling in 2026, so ‘first’ claims overlap. Company-reported.