Between 10 September and 16 October 2026, four organizations released time-series foundation models: Huawei’s Tabby, The Forecasting Company’s t0-gamma, Mistral’s Timestral, and JPMorgan Chase’s Morpheus-2.0. All four scale numerical inputs, divide them into patches, process them with transformers, and predict quantiles. The key architectural difference is how series communicate: Tabby forecasts each series independently, while Timestral and t0 exchange information between series in selected layers, and Morpheus does so in every layer.
This matters when temperature, promotions, or other known drivers could improve a forecast. The top three are difficult to separate on aggregate GIFT-Eval scores. Timestral leads on probabilistic CRPS, Morpheus on point-forecast MASE, and pairwise confidence intervals include a tie.
Training appears to explain much of the recent improvement. t0-gamma’s inference-time adjustments explain less than a tenth of its gain over t0-beta. Morpheus’s ablations and Tabby’s authors also point to data and training. Deployment constraints matter.
Licence, access to weights, support for covariates, and results on your own data can outweigh small leaderboard differences. A foundation model replaces fitting a model for each series. Traditionally, we might fit ARIMA or exponential smoothing to the substation’s historical readings, capturing daily and weekly patterns and tuning parameters to that location.
This can work well with enough history. Across 10,000 substations, however, fitting, monitoring, and updating separate models becomes expensive. A newly installed substation may have too little history for reliable local fitting.
A time-series foundation model is pretrained on many other series. At prediction time, it reads the substation’s recent history and produces a forecast in a forward pass, without updating its weights for that substation. This is zero-shot forecasting.
The analogy is to a language model handling a new piece of text without being retrained on that document.
Source: Towards Data Science · Summarized by HeadlinesBriefing