Math & Logic on MUSR (Performance %)
42.12MUSR PerformanceSFT
Evaluation Results
| Method | Links | |
|---|---|---|
| SFTMethod=Supervised Fine-Tuning2026.01 | 42.12 | |
| SPINIteration=Iter02026.01 | 41.67 | |
| Mistral-7BConfiguration=Base2026.01 | 41.27 | |
| SPINIteration=Iter22026.01 | 41.27 | |
| SPINIteration=Iter02026.01 | 41.26 | |
| T-SPINIteration=Iter02026.01 | 40.2 | |
| T-SPINIteration=Iter42026.01 | 39.72 | |
| SPINIteration=Iter12026.01 | 39.65 | |
| SPINIteration=Iter22026.01 | 39.64 | |
| SPINIteration=Iter32026.01 | 39.41 | |
| SFT2026.01 | 39.18 | |
| T-SPINIteration=Iter32026.01 | 39.18 | |
| SPINIteration=Iter12026.01 | 39.02 | |
| T-SPINIteration=Iter12026.01 | 38.95 | |
| Zephyr-7B2026.01 | 38.92 | |
| T-SPINIteration=Iter22026.01 | 38.91 | |
| T-SPINIteration=Iter22026.01 | 38.68 | |
| SPINIteration=Iter42026.01 | 38.59 | |
| T-SPINIteration=Iter32026.01 | 38.59 | |
| T-SPINIteration=Iter42026.01 | 38.46 | |
| SPINIteration=Iter42026.01 | 38.21 | |
| SPINIteration=Iter32026.01 | 37.93 | |
| T-SPINIteration=Iter12026.01 | 37.84 | |
| T-SPINIteration=Iter02026.01 | 37.05 |