Mathematical Reasoning on AMC (held-out)
85.9AccuracyMAPPA
Evaluation Results
| Method | Links | |
|---|---|---|
| MAPPABackbone=Qwen3-4B, Model Setup=Best2026.01 | 85.9 | |
| MAPPABackbone=R1-Distill-Qwen-1.5B, Model Setup=Best2026.01 | 78.1 | |
| Qwen3-4BModel Setup=Baseline2026.01 | 78.1 | |
| R1-Distill-Qwen-1.5BModel Setup=Baseline2026.01 | 60.9 |