Mathematical Problem Solving on Math500 (pass@8)
81.6Pass@8VI-CuRL
Evaluation Results
| Method | Links | |
|---|---|---|
| VI-CuRLModel=Qwen2.5-Math-7B, Verifier Setting=Majority Vote (w/o. Verifier)2026.02 | 81.6 | |
| No CurriculumModel=Qwen2.5-Math-7B, Verifier Setting=Majority Vote (w/o. Verifier)2026.02 | 81.4 | |
| VI-CuRLModel=Qwen2.5-Math-7B, Verifier Setting=Entropy (w/o. Verifier)2026.02 | 80.6 | |
| No CurriculumModel=Qwen2.5-Math-7B, Verifier Setting=Entropy (w/o. Verifier)2026.02 | 74.6 | |
| Base (No RL)Model=Qwen2.5-Math-7B, Verifier Setting=None2026.02 | 66.6 | |
| VI-CuRLModel=Llama3.2-3B-Instruct, Verifier Setting=Majority Vote (w/o. Verifier)2026.02 | 54.2 | |
| No CurriculumModel=Llama3.2-3B-Instruct, Verifier Setting=Majority Vote (w/o. Verifier)2026.02 | 50.6 | |
| VI-CuRLModel=Llama3.2-3B-Instruct, Verifier Setting=Entropy (w/o. Verifier)2026.02 | 50.2 | |
| Base (No RL)Model=Llama3.2-3B-Instruct, Verifier Setting=None2026.02 | 40.8 | |
| No CurriculumModel=Llama3.2-3B-Instruct, Verifier Setting=Entropy (w/o. Verifier)2026.02 | 3.2 |