List your company

Reasoning on PHYBENCH

26.26PHYBench ScoreT3S
19.281621.093322.90524.7167Jan 15, 2026

Evaluation results

MethodLinks
T3SDataset=S1K-200, Teacher Model=DeepSeek-R1, Student Model=Qwen3-8B2026.0126.26
T3SDataset=S1K-200, Teacher Model=QWQ, Student Model=Qwen3-8B2026.0124.36
T3SDataset=BOBA-200, Teacher Model=DeepSeek-R1, Student Model=Qwen3-8B2026.0123.95
T3SDataset=BOBA-200, Teacher Model=QWQ, Student Model=Qwen3-8B2026.0123.76
SFTDataset=S1K-200, Teacher Model=QWQ, Student Model=Qwen3-8B2026.0122.18
SFTDataset=BOBA-200, Teacher Model=DeepSeek-R1, Student Model=Qwen3-8B2026.0121.79
BaseStudent Model=Qwen3-8B2026.0120.47
SFTDataset=S1K-200, Teacher Model=DeepSeek-R1, Student Model=Qwen3-8B2026.0120.24
SFTDataset=BOBA-200, Teacher Model=QWQ, Student Model=Qwen3-8B2026.0119.55