yhatlabs/ChakraTS
Time Series Forecasting • Updated
AI & ML interests
Building foundation models for time series and tabular data, and systems that forecast real-world events.
Recent Activity
Organization Card
YHat Labs builds foundation AI models for tabular data: ChakraTS forecasts any time series and ChakraTab predicts on any table, pretrained, one API call, no training or tuning. We also build systems that forecast real-world events. This organization holds the model cards; benchmark records and reproduction code are on GitHub.
The Chakra model family
| Model | Data | What it does | Availability |
|---|---|---|---|
| ChakraTS | Time series | Zero-shot probabilistic forecasting: nine quantiles per step, known-future covariates, any regular frequency | API, commercial |
| ChakraTab | Tabular | Classification and regression with class probabilities | API, commercial |
| ChakraTS-Lab | Time series | Research configuration of ChakraTS, used for benchmark entries | Evaluation on request |
Benchmarks
We evaluate on the public leaderboards under their official protocols and publish the result files and the notebooks that regenerate them. Standing as of October 2026:
| Benchmark | Model | Standing |
|---|---|---|
| fev-bench | ChakraTS | 1st by win rate, 2nd by skill score |
| TIME | ChakraTS | 2nd of 31 |
| GIFT-Eval | ChakraTS | 3rd among non-agentic models |
| TabArena | ChakraTab | Top 5 (under review) |
Benchmark data is never used for anything other than scoring.
Contact
datasets 0
None public yet