List your company

Multi-task Model Evaluation on AIME24, AIME25, HMMT25, HE+, MBPP+ Average

58.4Average AccuracyTeacher Model
10.76823.13435.547.866Jun 21, 2026

Evaluation results

MethodLinks
Teacher ModelModel=Qwen3-4B-Instruct-2507, Teacher-Student Overlap=Large2026.0658.4
IW-OPDStudent Model=Qwen3-4B, Teacher Model=Qwen3-4B-Instruct-25072026.0655.3
IW-OPD10Student Model=Qwen3-4B, Training Step=10, Teacher Model=Qwen3-4B-Instruct-25072026.0655.1
OPDStudent Model=Qwen3-4B, Teacher Model=Qwen3-4B-Instruct-25072026.0654.3
OPD10Student Model=Qwen3-4B, Training Step=10, Teacher Model=Qwen3-4B-Instruct-25072026.0654
IW-OPDStudent Model=Qwen3-1.7B, Teacher Model=Qwen3-4B-Instruct-25072026.0639.1
BaseStudent Model=Qwen3-4B, Teacher Model=Qwen3-4B-Instruct-25072026.0638.9
IW-OPD10Student Model=Qwen3-1.7B, Training Step=10, Teacher Model=Qwen3-4B-Instruct-25072026.0638.1
OPDStudent Model=Qwen3-1.7B, Teacher Model=Qwen3-4B-Instruct-25072026.0637.9
OPD10Student Model=Qwen3-1.7B, Training Step=10, Teacher Model=Qwen3-4B-Instruct-25072026.0636.8
BaseStudent Model=Qwen3-1.7B, Teacher Model=Qwen3-4B-Instruct-25072026.0628.7
IW-OPDStudent Model=Qwen3-0.6B, Teacher Model=Qwen3-4B-Instruct-25072026.0621.9
IW-OPD10Student Model=Qwen3-0.6B, Training Step=10, Teacher Model=Qwen3-4B-Instruct-25072026.0620.6
OPDStudent Model=Qwen3-0.6B, Teacher Model=Qwen3-4B-Instruct-25072026.0620
OPD10Student Model=Qwen3-0.6B, Training Step=10, Teacher Model=Qwen3-4B-Instruct-25072026.0618.6
BaseStudent Model=Qwen3-0.6B, Teacher Model=Qwen3-4B-Instruct-25072026.0612.6