Spatial Reasoning on Open-Spatial
41ScoreDATAPROPHET
Evaluation results
| Method | Links | |
|---|---|---|
| DATAPROPHETRL Post-training Setup=Real RL, Data Selection Strategy=D.P.2026.03 | 41 | |
| BaselineRL Post-training Setup=Real RL, Data Selection Strategy=Equal2026.03 | 39 | |
| DATAPROPHETRL Post-training Setup=Synthetic RL, Data Selection Strategy=D.P.2026.03 | 37 | |
| BaselineRL Post-training Setup=Synthetic RL, Data Selection Strategy=Random2026.03 | 36 | |
| BaselineRL Post-training Setup=No RL, Data Selection Strategy=Baseline2026.03 | 35 |