Pending benchmarksTracking since Oct 19, 2026
Is Viggle JST-2 state of the art?Pending benchmarks.Announced Oct 19, 2026; no independent results yet.
Viggle's physics-native 3D world foundation model: scenes and characters with motion, built in 3D rather than pixel/video space.
Announced facts
The details so far
- Lab
- Viggle AI
- Announced
- Oct 19, 2026
- API
- Not yet
- Open weights
- Unknown
- Type
- Physics-native 3D world foundation model
- Claimed stack
- Full-stack model in 3D (lab wording); generate a 3D scene and expand it in real time
- Open weights
- Not stated in the announcement post; no matching Hugging Face JST-2 repo found at ingest
- API
- Not stated in the announcement post
Tags marked unsure are not stated on the lab's own pages.
Next steps
What would let us call it
Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.
- Publicly announced with a source
- Usable by the public (API or weights)
- Listed on an independent board we track
- Enough results for a rank in a category
- Holds across two snapshots (crowns only)
Self-reported
What the lab claims
Self-reported. Shown for context; not used in any verdict.
Lab claim: world's first full-stack physics-native world foundation model.
Receipts
Sources
LABViggle announcement on Xx.com/ViggleAI/status/2112202242048528540 · Oct 19, 2026LABViggle siteviggle.ai/ · Oct 19, 2026Tracking ends Jan 17, 2027 unless the API or weights become available.