List your company

Science Simulation on ScienceWorld

15.44Success RateBase
1.47285.09898.72512.3511Jun 17, 2026

Evaluation results

MethodLinks
BaseStudent Model=None, Teacher Model=Qwen3-32B2026.0615.44-17.9218.67
BaseStudent Model=None, Teacher Model=Qwen3-8B2026.0610.74-16.0921.67
SAGE-OPDStudent Model=Qwen3-1.7B, Teacher Model=Qwen3-32B2026.067.38-16.0120.91
SAGE-OPDStudent Model=Qwen3-1.7B, Teacher Model=Qwen3-8B2026.066.710.2425.3
Entropy-Aware OPDStudent Model=Qwen3-0.6B, Teacher Model=Qwen3-32B2026.066.04-26.120
SAGE-OPDStudent Model=Qwen3-0.6B, Teacher Model=Qwen3-32B2026.066.04-26.120
TCOD-F2BStudent Model=Qwen3-1.7B, Teacher Model=Qwen3-32B2026.066.04-14.8922.02
OPDStudent Model=Qwen3-1.7B, Teacher Model=Qwen3-8B2026.064.7-2.7825.12
TCOD-F2BStudent Model=Qwen3-1.7B, Teacher Model=Qwen3-8B2026.064.7-9.6824.06
OPDStudent Model=Qwen3-1.7B, Teacher Model=Qwen3-32B2026.064.03-29.8919.64
BaseStudent Model=Qwen3-0.6B, Teacher Model=None2026.063.36-43.5121.38
BaseStudent Model=Qwen3-1.7B, Teacher Model=None2026.063.36-2421.38
Entropy-Aware OPDStudent Model=Qwen3-0.6B, Teacher Model=Qwen3-8B2026.063.36-11.5223.44
Entropy-Aware OPDStudent Model=Qwen3-1.7B, Teacher Model=Qwen3-8B2026.063.36-3.1325.91
OPDStudent Model=Qwen3-0.6B, Teacher Model=Qwen3-32B2026.063.36-28.4620.79
Entropy-Aware OPDStudent Model=Qwen3-1.7B, Teacher Model=Qwen3-32B2026.063.36-14.9923.59
TCOD-F2BStudent Model=Qwen3-0.6B, Teacher Model=Qwen3-8B2026.063.03-2.0724.88
TCOD-F2BStudent Model=Qwen3-0.6B, Teacher Model=Qwen3-32B2026.062.68-33.4223.2
SFTStudent Model=Qwen3-0.6B, Teacher Model=Qwen3-8B2026.062.01-31.8423.94
OPDStudent Model=Qwen3-0.6B, Teacher Model=Qwen3-8B2026.062.01-12.8823.94
SAGE-OPDStudent Model=Qwen3-0.6B, Teacher Model=Qwen3-8B2026.062.013.8926.94
SFTStudent Model=Qwen3-1.7B, Teacher Model=Qwen3-8B2026.062.01-17.5623.28
SFTStudent Model=Qwen3-0.6B, Teacher Model=Qwen3-32B2026.062.01-34.5918.1
SFTStudent Model=Qwen3-1.7B, Teacher Model=Qwen3-32B2026.062.01-15.6123.23