Mathematical Reasoning on WizardMath (test)
43Math ScoreTRAP
Evaluation Results
| Method | Links | |
|---|---|---|
| TRAPalpha=0.10, merging_technique=TIES-merging, DARE=false2024.10 | 43 | |
| IFalpha=0.10, merging_technique=Task Arithmetic, DARE=false2024.10 | 43 | |
| IFalpha=0.10, merging_technique=Task Arithmetic, DARE=true2024.10 | 43 | |
| TRAPalpha=0.10, merging_technique=Task Arithmetic, DARE=false2024.10 | 42 | |
| TRAPalpha=0.30, merging_technique=Task Arithmetic, DARE=false2024.10 | 42 | |
| TRAPalpha=0.10, merging_technique=Task Arithmetic, DARE=true2024.10 | 42 | |
| TRAPalpha=0.30, merging_technique=Task Arithmetic, DARE=true2024.10 | 42 | |
| IFalpha=0.10, merging_technique=TIES-merging, DARE=false2024.10 | 42 | |
| IFalpha=0.10, merging_technique=TIES-merging, DARE=true2024.10 | 42 | |
| MERGEPRINTalpha=0.10, merging_technique=Task Arithmetic, DARE=false2024.10 | 42 | |
| MERGEPRINTalpha=0.30, merging_technique=Task Arithmetic, DARE=false2024.10 | 42 | |
| MERGEPRINTalpha=0.10, merging_technique=Task Arithmetic, DARE=true2024.10 | 42 | |
| MERGEPRINTalpha=0.30, merging_technique=Task Arithmetic, DARE=true2024.10 | 42 | |
| MERGEPRINTalpha=0.10, merging_technique=TIES-merging, DARE=false2024.10 | 42 | |
| TRAPalpha=0.30, merging_technique=TIES-merging, DARE=false2024.10 | 41 | |
| IFalpha=0.30, merging_technique=Task Arithmetic, DARE=false2024.10 | 41 | |
| IFalpha=0.30, merging_technique=Task Arithmetic, DARE=true2024.10 | 41 | |
| IFalpha=0.30, merging_technique=TIES-merging, DARE=false2024.10 | 40 | |
| MERGEPRINTalpha=0.30, merging_technique=TIES-merging, DARE=false2024.10 | 40 | |
| IFalpha=0.30, merging_technique=TIES-merging, DARE=true2024.10 | 39 | |
| TRAPalpha=0.50, merging_technique=Task Arithmetic, DARE=false2024.10 | 38 | |
| TRAPalpha=0.50, merging_technique=Task Arithmetic, DARE=true2024.10 | 38 | |
| TRAPalpha=0.10, merging_technique=TIES-merging, DARE=true2024.10 | 38 | |
| TRAPalpha=0.30, merging_technique=TIES-merging, DARE=true2024.10 | 38 | |
| IFalpha=0.50, merging_technique=Task Arithmetic, DARE=false2024.10 | 38 | |
| IFalpha=0.50, merging_technique=Task Arithmetic, DARE=true2024.10 | 38 | |
| IFalpha=0.50, merging_technique=TIES-merging, DARE=true2024.10 | 38 | |
| MERGEPRINTalpha=0.50, merging_technique=Task Arithmetic, DARE=false2024.10 | 38 | |
| MERGEPRINTalpha=0.50, merging_technique=Task Arithmetic, DARE=true2024.10 | 38 | |
| MERGEPRINTalpha=0.10, merging_technique=TIES-merging, DARE=true2024.10 | 38 | |
| MERGEPRINTalpha=0.30, merging_technique=TIES-merging, DARE=true2024.10 | 38 | |
| TRAPalpha=0.90, merging_technique=TIES-merging, DARE=false2024.10 | 36 | |
| TRAPalpha=0.50, merging_technique=TIES-merging, DARE=true2024.10 | 36 | |
| IFalpha=0.50, merging_technique=TIES-merging, DARE=false2024.10 | 36 | |
| MERGEPRINTalpha=0.50, merging_technique=TIES-merging, DARE=false2024.10 | 36 | |
| MERGEPRINTalpha=0.90, merging_technique=TIES-merging, DARE=false2024.10 | 36 | |
| TRAPalpha=0.50, merging_technique=TIES-merging, DARE=false2024.10 | 35 | |
| TRAPalpha=0.70, merging_technique=TIES-merging, DARE=false2024.10 | 35 | |
| IFalpha=0.90, merging_technique=TIES-merging, DARE=false2024.10 | 35 | |
| MERGEPRINTalpha=0.70, merging_technique=TIES-merging, DARE=false2024.10 | 35 | |
| MERGEPRINTalpha=0.50, merging_technique=TIES-merging, DARE=true2024.10 | 35 | |
| IFalpha=0.70, merging_technique=TIES-merging, DARE=false2024.10 | 34 | |
| IFalpha=0.70, merging_technique=TIES-merging, DARE=true2024.10 | 34 | |
| MERGEPRINTalpha=0.70, merging_technique=Task Arithmetic, DARE=false2024.10 | 34 | |
| MERGEPRINTalpha=0.70, merging_technique=Task Arithmetic, DARE=true2024.10 | 34 | |
| TRAPalpha=0.70, merging_technique=Task Arithmetic, DARE=false2024.10 | 33 | |
| TRAPalpha=0.70, merging_technique=Task Arithmetic, DARE=true2024.10 | 33 | |
| TRAPalpha=0.70, merging_technique=TIES-merging, DARE=true2024.10 | 33 | |
| TRAPalpha=0.90, merging_technique=TIES-merging, DARE=true2024.10 | 33 | |
| IFalpha=0.90, merging_technique=TIES-merging, DARE=true2024.10 | 33 | |
| MERGEPRINTalpha=0.70, merging_technique=TIES-merging, DARE=true2024.10 | 33 | |
| MERGEPRINTalpha=0.90, merging_technique=TIES-merging, DARE=true2024.10 | 33 | |
| IFalpha=0.70, merging_technique=Task Arithmetic, DARE=false2024.10 | 32 | |
| IFalpha=0.70, merging_technique=Task Arithmetic, DARE=true2024.10 | 32 | |
| MERGEPRINTalpha=0.90, merging_technique=Task Arithmetic, DARE=false2024.10 | 27 | |
| MERGEPRINTalpha=0.90, merging_technique=Task Arithmetic, DARE=true2024.10 | 27 | |
| TRAPalpha=0.90, merging_technique=Task Arithmetic, DARE=false2024.10 | 26 | |
| TRAPalpha=0.90, merging_technique=Task Arithmetic, DARE=true2024.10 | 26 | |
| IFalpha=0.90, merging_technique=Task Arithmetic, DARE=false2024.10 | 24 | |
| IFalpha=0.90, merging_technique=Task Arithmetic, DARE=true2024.10 | 24 |