List your company

Mathematical Reasoning on AIME 25 (Pass@1, Pass@4, Pass@8)

40Pass@8MOTAB
5.336814.335923.33532.3341May 19, 2026

Evaluation results

MethodLinks
MOTABStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B2026.054032.0514.58
ImitKDStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B2026.0536.6728.3312.5
SKDStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B, beta=0.82026.0536.6728.2413.33
RFTStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B2026.0533.3324.6712.08
SKDStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B, beta=1.02026.0533.3323.99.17
SFTStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B2026.0526.6722.2911.25
SKDStudent LLM=Qwen3-1.7B, Teacher Model=Qwen3-32B, beta=0.62026.0526.6722.339.59
ImitKDStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B2026.0526.6716.575.83
SKDStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B, beta=0.82026.0526.6718.817.5
MOTABStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B2026.0526.6719.527.92
SKDStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B, beta=0.62026.0523.3317.867.92
SKDStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B, beta=1.02026.0523.3317.146.67
RFTStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B2026.0520145
MOTABStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B2026.0516.67——
SFTStudent LLM=Qwen2.5-7B-Instruct, Teacher Model=Qwen3-32B2026.0516.67104.58
SKDStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B, beta=0.82026.0513.339.052.92
SFTStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B2026.056.673.330.83
RFTStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B2026.056.673.330.83
ImitKDStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B2026.056.674.761.67
SKDStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B, beta=0.62026.056.674.952.08
SKDStudent LLM=Llama3.2-3B-Instruct, Teacher Model=Qwen3-32B, beta=1.02026.056.675.241.67