Timestral releases four open time-series models, topping GIFT-Eval
Authors say the 209M and 123M variants rank first and second on every metric of GIFT-Eval, TIME, and fev-bench.
58
Authors say the 209M and 123M variants rank first and second on every metric of GIFT-Eval, TIME, and fev-bench.
Mistral says its 209M model ranks first on GIFT-Eval, TIME and fev-bench while using about two-thirds the parameters of the prior leader.
The title says the family outperforms Google’s TimesFM-3; the article body was not in the provided text.
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.
Today 2.1K readers · 11K views · 8.3K reads · all time 157K views