General Reasoning and Language Modeling on FineWeb Edu
25.37ARC-cSAW
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| SAWG1=true, G2=true, G3=true, G4=true2026.05 | 25.37 | 39.86 | 28.44 | 14.65 | 29 | 57.72 | 63.5 | 51.64 | 38.78 | |
| STRG1=true, G2=true, G3=false, G4=true2026.05 | 25.09 | 39.73 | 28.55 | 14.09 | 28 | 57.94 | 63.4 | 52.41 | 38.65 | |
| DELTG1=true, G2=true, G3=false, G4=false2026.05 | 24.15 | 38.38 | 28.09 | 10.69 | 29.4 | 55.82 | 61.2 | 51.07 | 37.35 | |
| CLG1=true, G2=false, G3=true, G4=false2026.05 | 23.11 | 38.63 | 28.1 | 13.85 | 28.4 | 57.42 | 60.1 | 51.5 | 37.61 | |
| RandomG1=false, G2=true, G3=false, G4=true2026.05 | 21.47 | 37.5 | 27.57 | 15.97 | 25.6 | 57.8 | 59.5 | 51.13 | 37.09 |