Mathematical Reasoning on MATH (test) (Exact Match)
76.1Exact Match (EM)Anchor-Points
Evaluation Results
| Method | Links | |
|---|---|---|
| Anchor-PointsOptimization Budget=Large2026.01 | 76.1 | |
| SESS-wrepOptimization Budget=Small2026.01 | 76.1 | |
| SESS-vlcOptimization Budget=Small2026.01 | 75.7 | |
| SESS-vlcOptimization Budget=Large2026.01 | 75.7 | |
| SESS-lcOptimization Budget=Large2026.01 | 75.3 | |
| Anchor-PointsOptimization Budget=Small2026.01 | 75.1 | |
| IPOMPOptimization Budget=Large2026.01 | 74.7 | |
| RandomOptimization Budget=Small2026.01 | 74.1 | |
| SESS-lcOptimization Budget=Small2026.01 | 73.9 | |
| IPOMPOptimization Budget=Small2026.01 | 73.7 | |
| SESS-wrepOptimization Budget=Large2026.01 | 73.6 | |
| RandomOptimization Budget=Large2026.01 | 73.3 | |
| BaseOptimization Budget=Small2026.01 | 73.2 | |
| BaseOptimization Budget=Large2026.01 | 73.2 | |
| SESS-repOptimization Budget=Small2026.01 | 73.2 | |
| SESS-repOptimization Budget=Large2026.01 | 70.3 |