Mathematical Reasoning on MATH-500 (In-distribution)
77AccRLTR
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| RLTRSamples for Acc.=642026.02 | 77 | 79 | 83.8 | 84.2 | |
| RLVRSamples for Acc.=642026.02 | 76.2 | 78.2 | 80.2 | 82.2 | |
| Base modelSamples for Acc.=642026.02 | 71 | 78 | 81.2 | 82.6 |
| Method | Links | ||||
|---|---|---|---|---|---|
| RLTRSamples for Acc.=642026.02 | 77 | 79 | 83.8 | 84.2 | |
| RLVRSamples for Acc.=642026.02 | 76.2 | 78.2 | 80.2 | 82.2 | |
| Base modelSamples for Acc.=642026.02 | 71 | 78 | 81.2 | 82.6 |