List your company

Scientific Question Answering on GPQA-D (Accuracy)

14.43Accuracy (GPQA-D)IOA
6.82768.801310.77512.7487Feb 12, 2026

Evaluation results

MethodLinks
IOAStudent Model=Qwen2.5-3B, Teacher Model=DeepSeek-R12026.0214.43
IOAStudent Model=LLaMA3.2-3B, Teacher Model=DeepSeek-R12026.0212.47
MADAStudent Model=Qwen2.5-3B, Teacher Model=DeepSeek-R12026.0212.27
Star-AgentsStudent Model=Qwen2.5-3B, Teacher Model=DeepSeek-R12026.0211.92
CasCoDStudent Model=Qwen2.5-3B, Teacher Model=DeepSeek-R12026.0211.54
CounterDistillStudent Model=Qwen2.5-3B, Teacher Model=DeepSeek-R12026.0211.29
DSSStudent Model=Qwen2.5-3B, Teacher Model=DeepSeek-R12026.0211.18
MADAStudent Model=LLaMA3.2-3B, Teacher Model=DeepSeek-R12026.0211.13
Star-AgentsStudent Model=LLaMA3.2-3B, Teacher Model=DeepSeek-R12026.0210.94
CasCoDStudent Model=LLaMA3.2-3B, Teacher Model=DeepSeek-R12026.0210.72
LionStudent Model=Qwen2.5-3B, Teacher Model=DeepSeek-R12026.0210.62
CounterDistillStudent Model=LLaMA3.2-3B, Teacher Model=DeepSeek-R12026.0210.51
DSSStudent Model=LLaMA3.2-3B, Teacher Model=DeepSeek-R12026.0210.37
LionStudent Model=LLaMA3.2-3B, Teacher Model=DeepSeek-R12026.029.93
LaMiniStudent Model=Qwen2.5-3B, Teacher Model=DeepSeek-R12026.029.63
Self-InstructStudent Model=Qwen2.5-3B, Teacher Model=DeepSeek-R12026.029.26
LaMiniStudent Model=LLaMA3.2-3B, Teacher Model=DeepSeek-R12026.028.94
Self-InstructStudent Model=LLaMA3.2-3B, Teacher Model=DeepSeek-R12026.028.52
UndistilledStudent Model=Qwen2.5-3B, Teacher Model=None2026.027.94
UndistilledStudent Model=LLaMA3.2-3B, Teacher Model=None2026.027.12