List your company

Math Reasoning on AIME 2025 (avg@32 and pass@32)

38.44Avg Score @32SG-OPD
25.107228.568632.0335.4914Jun 8, 2026

Evaluation results

MethodLinks
SG-OPDSetting=Strong-to-weak, Teacher=Qwen3-4B-Non-Thinking-RL-Math, Student=Qwen3-1.7B, Training steps=5002026.0638.4466.67
OPDSetting=Strong-to-weak, Teacher=Qwen3-4B-Non-Thinking-RL-Math, Student=Qwen3-1.7B, Training steps=5002026.0633.4450
ExOPDSetting=Strong-to-weak, Teacher=Qwen3-4B-Non-Thinking-RL-Math, Student=Qwen3-1.7B, Training steps=5002026.0633.1253.33
GKDSetting=Strong-to-weak, Teacher=Qwen3-4B-Non-Thinking-RL-Math, Student=Qwen3-1.7B, Training steps=5002026.0632.1950
SeqKDSetting=Strong-to-weak, Teacher=Qwen3-4B-Non-Thinking-RL-Math, Student=Qwen3-1.7B, Training steps=5002026.0626.4636.67
SFTSetting=Strong-to-weak, Teacher=Qwen3-4B-Non-Thinking-RL-Math, Student=Qwen3-1.7B, Training steps=5002026.0625.6233.67