Multi-Domain Knowledge on MMLU-Pro
31.42PerformanceT-SPIN
Evaluation Results
| Method | Links | |
|---|---|---|
| T-SPINIteration=Iter32026.01 | 31.42 | |
| T-SPINIteration=Iter42026.01 | 31.34 | |
| T-SPINIteration=Iter22026.01 | 30.52 | |
| T-SPINIteration=Iter02026.01 | 30.47 | |
| T-SPINIteration=Iter12026.01 | 30.45 | |
| SPINIteration=Iter02026.01 | 30.36 | |
| SFTMethod=Supervised Fine-Tuning2026.01 | 30.18 | |
| Mistral-7BConfiguration=Base2026.01 | 29.99 | |
| SPINIteration=Iter42026.01 | 29.9 | |
| SPINIteration=Iter22026.01 | 29.82 | |
| SPINIteration=Iter12026.01 | 29.8 | |
| SPINIteration=Iter32026.01 | 29.64 | |
| T-SPINIteration=Iter32026.01 | 29.37 | |
| T-SPINIteration=Iter42026.01 | 29.32 | |
| T-SPINIteration=Iter22026.01 | 29.26 | |
| SFT2026.01 | 29.19 | |
| T-SPINIteration=Iter12026.01 | 29.13 | |
| Zephyr-7B2026.01 | 28.88 | |
| T-SPINIteration=Iter02026.01 | 28.88 | |
| SPINIteration=Iter22026.01 | 28.67 | |
| SPINIteration=Iter02026.01 | 28.39 | |
| SPINIteration=Iter32026.01 | 27.98 | |
| SPINIteration=Iter12026.01 | 27.88 | |
| SPINIteration=Iter42026.01 | 25.95 |