Skip to main content

Results

Mean and median R² across 96 regression tasks from three public benchmark suites (6M-parameter model):
SuiteDatasetsMean R²Median R²
TabArena130.81170.8757
TALENT720.75690.8802
OpenML110.63730.5856
Overall960.75060.8702
These results are for the ~6M base model. A larger Nori-30M variant is also available (model="nori-30m", see the Quickstart) — its published results are on its model card.

Reproducing these numbers

Coming soon.