List your company

Mathematical Reasoning on MATH 500 (L1-L5 Scores)

90.7L1 ScoreSFT
73.768878.164482.5686.9556May 19, 2026

Evaluation results

MethodLinks
SFTStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B2026.0590.784.4473.3367.9743.28
SKDStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B, beta=0.62026.0590.783.3377.1466.4145.52
MOTABStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B2026.0590.793.3382.8678.9158.21
MOTABStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B2026.0590.784.4481.967.1948.51
SKDStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B, beta=0.82026.0588.3785.5676.1968.7544.03
SKDStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B, beta=0.82026.0588.3763.3359.055023.88
RFTStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B2026.0588.3782.2280.9558.5935.07
SKDStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B, beta=0.82026.0588.3781.1173.3369.5335.07
SKDStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B, beta=1.02026.0586.0576.6769.5260.1641.04
MOTABStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B2026.0586.0568.8960.9548.4428.36
SKDStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B, beta=1.02026.0586.0577.7872.3864.0641.79
SKDStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B, beta=1.02026.0583.7258.8952.3834.3817.91
SFTStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B2026.0583.7274.4469.5260.1644.78
SKDStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B, beta=0.62026.0583.7283.3375.2465.6233.58
RFTStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B2026.0581.475.5674.2966.4141.04
ImitKDStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B2026.0581.4808059.3848.51
SFTStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B2026.0579.0753.3351.4342.1922.39
ImitKDStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B2026.0576.7466.6757.1440.6217.91
SKDStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B, beta=0.62026.0576.6468.8958.142.9715.67
RFTStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B2026.0574.4258.8959.0542.1920.9
ImitKDStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B2026.0574.427072.3857.8135.82