​
Models with Covariates Support

These models can incorporate external variables (covariates) to improve forecasting accuracy.
ModelDescriptionUse CaseModel IDPaper
TabPFN-TSFoundation model from University of FreiburgBest for general forecasting tasks, financial data, and scenarios where external variables significantly impact outcomes. Leverages transformer architecture for complex pattern recognition.forecast-model-4TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second

​
Models without Covariates

These models work with univariate time series data and are optimized for specific use cases.
ModelDescriptionUse CaseModel IDPaper
chronos-boltAmazon’s lightweight Chronos modelBest for real-time forecasting and IoT sensor data requiring low latency predictions. Provides fast inference times with minimal computational overhead.forecast-model-2Chronos: Learning the Language of Time Series
TiRexNXAI’s model based on xLSTMsBest for complex seasonal data and long-term forecasting with intricate cyclical patterns. Designed to capture complex temporal dependencies.forecast-model-3TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
TOTODatadog’s observability-optimized modelBest for DevOps monitoring, infrastructure metrics, and application performance data. Tailored for observability-related forecasting needs.forecast-model-1TOTO: Time Series Optimized Transformer for Observability
More models coming soon!

​
Model Performance

Each model is optimized for different scenarios:
  • TabPFN-TS: Best overall performance for complex forecasting tasks
  • chronos-bolt: Fastest inference times for real-time applications
  • TiRex: Superior performance on seasonal and cyclical data
  • TOTO: Optimized for observability and monitoring use cases