Mathematical Reasoning on AMC Out-of-distribution 2023 (test)
0.535AccuracyRLTR
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| RLTRevaluation_samples=642026.02 | 0.535 | 0.592 | 0.667 | 0.675 | |
| RLVRevaluation_samples=642026.02 | 0.528 | 0.558 | 0.625 | 0.617 | |
| Base modelevaluation_samples=642026.02 | 0.462 | 0.517 | 0.592 | 0.608 |