Mathematical Reasoning on AIME 25 (Avg@8, Pass@8)
2.08Average Score @8GRPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GRPOStudent Model=Llama-3.2-3B-Instruct, Teacher Model=Llama-3.1-8B-Instruct2026.03 | 2.08 | 10 | |
| EOPDStudent Model=Llama-3.2-3B-Instruct, Teacher Model=Llama-3.1-8B-Instruct2026.03 | 2.08 | 10 | |
| KDStudent Model=Llama-3.2-3B-Instruct, Teacher Model=Llama-3.1-8B-Instruct2026.03 | 1.25 | 6.66 | |
| OPDStudent Model=Llama-3.2-3B-Instruct, Teacher Model=Llama-3.1-8B-Instruct2026.03 | 1.25 | 6.66 |