Results
Mean and median R² across 96 regression tasks from three public benchmark suites (6M-parameter model):| Suite | Datasets | Mean R² | Median R² |
|---|---|---|---|
| TabArena | 13 | 0.8117 | 0.8757 |
| TALENT | 72 | 0.7569 | 0.8802 |
| OpenML | 11 | 0.6373 | 0.5856 |
| Overall | 96 | 0.7506 | 0.8702 |
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.