Math & Logic on MATH (Performance %)
4.56Performance (%)SPIN
Evaluation Results
| Method | Links | |
|---|---|---|
| SPINIteration=Iter42026.01 | 4.56 | |
| T-SPINIteration=Iter42026.01 | 3.94 | |
| T-SPINIteration=Iter32026.01 | 3.85 | |
| SPINIteration=Iter32026.01 | 3.71 | |
| T-SPINIteration=Iter02026.01 | 3.53 | |
| SPINIteration=Iter22026.01 | 3.5 | |
| SPINIteration=Iter12026.01 | 3.43 | |
| T-SPINIteration=Iter22026.01 | 3.43 | |
| T-SPINIteration=Iter12026.01 | 3.32 | |
| Mistral-7BConfiguration=Base2026.01 | 3.27 | |
| SFTMethod=Supervised Fine-Tuning2026.01 | 3.08 | |
| SPINIteration=Iter02026.01 | 2.86 |