List your company

Mathematical Reasoning on HMMT-26 (mean@8, pass@8)

43.94Mean@8DeepSeek-R1-Distill-Qwen-32B
11.242419.731228.2236.7088May 29, 2026

Evaluation results

MethodLinks
DeepSeek-R1-Distill-Qwen-32B2026.0543.9463.64
SkyWork-OR1-Math-7B2026.0536.7454.55
GRPOStudent Model=DeepSeek-R1-Distill-Qwen-7B, Teacher Model=DeepSeek-R1-Distill-Qwen-32B2026.0536.7454.55
LGRStudent Model=DeepSeek-R1-Distill-Qwen-7B, Teacher Model=DeepSeek-R1-Distill-Qwen-32B2026.0534.8551.52
OPD (9k)Student Model=DeepSeek-R1-Distill-Qwen-7B, Teacher Model=DeepSeek-R1-Distill-Qwen-32B2026.0532.9545.45
REOPOLDStudent Model=DeepSeek-R1-Distill-Qwen-7B, Teacher Model=DeepSeek-R1-Distill-Qwen-32B2026.0532.9546.88
JSDStudent Model=DeepSeek-R1-Distill-Qwen-7B, Teacher Model=DeepSeek-R1-Distill-Qwen-32B2026.0531.8242.42
LGR (topk)Student Model=DeepSeek-R1-Distill-Qwen-7B, Teacher Model=DeepSeek-R1-Distill-Qwen-32B2026.0530.6836.36
OPD (topk)Student Model=DeepSeek-R1-Distill-Qwen-7B, Teacher Model=DeepSeek-R1-Distill-Qwen-32B2026.0530.342.42
Base ModelStudent Model=DeepSeek-R1-Distill-Qwen-7B2026.0528.0339.39
LGR (topk)Student Model=DeepSeek-R1-Distill-Qwen-1.5B, Teacher Model=SkyWork-OR1-Math-7B2026.0524.6234.38
LGRStudent Model=DeepSeek-R1-Distill-Qwen-1.5B, Teacher Model=SkyWork-OR1-Math-7B2026.0523.8637.5
OPD (9k)Student Model=DeepSeek-R1-Distill-Qwen-1.5B, Teacher Model=SkyWork-OR1-Math-7B2026.0522.7327.27
REOPOLDStudent Model=DeepSeek-R1-Distill-Qwen-1.5B, Teacher Model=SkyWork-OR1-Math-7B2026.0522.3527.27
OPD (topk)Student Model=DeepSeek-R1-Distill-Qwen-1.5B, Teacher Model=SkyWork-OR1-Math-7B2026.0521.5933.33
JSDStudent Model=DeepSeek-R1-Distill-Qwen-1.5B, Teacher Model=SkyWork-OR1-Math-7B2026.0521.2133.33
GRPOStudent Model=DeepSeek-R1-Distill-Qwen-1.5B, Teacher Model=SkyWork-OR1-Math-7B2026.0520.4627.27
Base ModelStudent Model=DeepSeek-R1-Distill-Qwen-1.5B2026.0512.527.27