Multi-Domain Knowledge on GPQA
31.06PerformanceT-SPIN
Evaluation Results
| Method | Links | |
|---|---|---|
| T-SPINIteration=Iter42026.01 | 31.06 | |
| T-SPINIteration=Iter22026.01 | 30.92 | |
| T-SPINIteration=Iter32026.01 | 30.83 | |
| T-SPINIteration=Iter42026.01 | 30.44 | |
| T-SPINIteration=Iter32026.01 | 30.12 | |
| Mistral-7BConfiguration=Base2026.01 | 29.86 | |
| SPINIteration=Iter02026.01 | 29.53 | |
| SPINIteration=Iter02026.01 | 29.47 | |
| T-SPINIteration=Iter22026.01 | 29.4 | |
| T-SPINIteration=Iter12026.01 | 29.1 | |
| SPINIteration=Iter12026.01 | 29.06 | |
| T-SPINIteration=Iter12026.01 | 28.92 | |
| Zephyr-7B2026.01 | 28.91 | |
| T-SPINIteration=Iter02026.01 | 28.82 | |
| SPINIteration=Iter32026.01 | 28.77 | |
| SPINIteration=Iter42026.01 | 28.73 | |
| SPINIteration=Iter22026.01 | 28.39 | |
| SPINIteration=Iter12026.01 | 28.33 | |
| SFT2026.01 | 28.28 | |
| T-SPINIteration=Iter02026.01 | 28.05 | |
| SPINIteration=Iter22026.01 | 28 | |
| SFTMethod=Supervised Fine-Tuning2026.01 | 27.98 | |
| SPINIteration=Iter32026.01 | 27.61 | |
| SPINIteration=Iter42026.01 | 26.21 |