Mathematical Reasoning on AIME24 (Pass@8, Pass@4, Pass@1)
50Pass@8MOTAB
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MOTABStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B2026.05 | 50 | 41.38 | 22.08 | |
| SKDStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B, beta=0.82026.05 | 43.33 | 34.71 | 14.58 | |
| SFTStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B2026.05 | 36.67 | 25.9 | 9.58 | |
| ImitKDStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B2026.05 | 36.67 | 30.19 | 16.25 | |
| MOTABStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B2026.05 | 30 | 23.33 | 10.42 | |
| SKDStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B, beta=0.82026.05 | 26.67 | 22.05 | 10 | |
| SKDStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B, beta=0.62026.05 | 23.33 | 17.57 | 7.92 | |
| SKDStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B, beta=1.02026.05 | 23.33 | 18.57 | 10.83 | |
| MOTABStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B2026.05 | 23.33 | 13.76 | 5 | |
| SFTStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B2026.05 | 23.33 | 19.76 | 10.42 | |
| SKDStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B, beta=0.62026.05 | 23.33 | 19.24 | 10 | |
| SKDStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B, beta=0.82026.05 | 20 | 11.67 | 2.92 | |
| ImitKDStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B2026.05 | 20 | 16.19 | 5.83 | |
| SKDStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B, beta=1.02026.05 | 20 | 13.33 | 4.17 | |
| SFTStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B2026.05 | 16.67 | 11.19 | 3.33 | |
| ImitKDStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B2026.05 | 16.67 | 9.76 | 2.92 | |
| SKDStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B, beta=0.62026.05 | 16.67 | 8.33 | 2.08 | |
| SKDStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B, beta=1.02026.05 | 16.67 | 12.38 | 3.75 | |
| RFTStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B2026.05 | 16.67 | 12.86 | 5.42 | |
| RFTStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B2026.05 | 13.33 | 11.38 | 5.83 | |
| RFTStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B2026.05 | 10 | 7.38 | 2.5 |