Pending benchmarksTracking since Oct 19, 2026
Is Morpheus-2.0 state of the art?Pending benchmarks.Announced Oct 19, 2026; no independent results yet.
A time-series forecasting foundation model from a JPMorgan Chase team, announced in a thread by a team member. Not an LLM. Weights and API not stated; paper coming soon.
Announced facts
The details so far
- Lab
- JPMorgan Chase
- Announced
- Oct 19, 2026
- API
- Not yet
- Open weights
- Unknown
- Focus
- Time-series forecasting (foundation model)
- Architecture
- Dual-axis attention across time and variables, with 2D positional embeddings (team thread)
- Training
- Adaptive resolution and horizon-adaptive training (team thread)
- Inputs
- Multivariate, with any number of covariates (team thread)
- GIFT-Eval
- Results listed on the GIFT-Eval leaderboard (added 2026-10-16)
- Weights / API
- Not stated
- Paper
- Coming soon (team thread)
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.
Team claim: #1 in forecasting accuracy among foundation models on the GIFT-Eval leaderboard (thread by a JPMorgan Chase team member).
Receipts
Sources
PRESSAnnouncement thread on X by a JPMorgan Chase team memberx.com/Aakriti2810/status/2112280512597545183 · Oct 19, 2026Tracking ends Jan 17, 2027 unless the API or weights become available.