Mathematical Problem Solving on AMC 2023
88.2Pass@8VI-CuRL
Evaluation Results
| Method | Links | |
|---|---|---|
| VI-CuRLModel=Qwen2.5-Math-7B, Verifier Setting=Majority Vote (w/o. Verifier)2026.02 | 88.2 | |
| VI-CuRLModel=Qwen2.5-Math-7B, Verifier Setting=Entropy (w/o. Verifier)2026.02 | 85 | |
| No CurriculumModel=Qwen2.5-Math-7B, Verifier Setting=Majority Vote (w/o. Verifier)2026.02 | 82.8 | |
| Base (No RL)Model=Qwen2.5-Math-7B, Verifier Setting=None2026.02 | 81.9 | |
| No CurriculumModel=Qwen2.5-Math-7B, Verifier Setting=Entropy (w/o. Verifier)2026.02 | 71.5 | |
| VI-CuRLModel=Llama3.2-3B-Instruct, Verifier Setting=Majority Vote (w/o. Verifier)2026.02 | 58.1 | |
| VI-CuRLModel=Llama3.2-3B-Instruct, Verifier Setting=Entropy (w/o. Verifier)2026.02 | 56.9 | |
| Base (No RL)Model=Llama3.2-3B-Instruct, Verifier Setting=None2026.02 | 54.7 | |
| No CurriculumModel=Llama3.2-3B-Instruct, Verifier Setting=Majority Vote (w/o. Verifier)2026.02 | 53.8 | |
| No CurriculumModel=Llama3.2-3B-Instruct, Verifier Setting=Entropy (w/o. Verifier)2026.02 | 15.9 |