List your company

Data Contamination Detection on SAT

79F1 ScoreEntropy-Noise
-3.1618.1739.560.83Oct 10, 2025

Evaluation results

MethodLinks
Entropy-NoiseTarget Model=Qwen2.5-7B-Instruct2025.107977
Self-CritiqueTarget Model=Qwen2.5-7B-Instruct2025.106967
Min-K%Target Model=DeepSeek-Math-7B-Instruct2025.106935
RecallTarget Model=DeepSeek-Math-7B-Instruct2025.106962
PPLTarget Model=DeepSeek-Math-7B-Instruct2025.106864
Entropy-NoiseTarget Model=DeepSeek-Math-7B-Instruct2025.106745
Entropy-TempTarget Model=Qwen2.5-7B-Instruct2025.106669
CDDTarget Model=DeepSeek-Math-7B-Instruct2025.106650
Self-CritiqueTarget Model=DeepSeek-Math-7B-Instruct2025.106667
Entropy-TempTarget Model=DeepSeek-Math-7B-Instruct2025.106461
RecallTarget Model=Qwen2.5-7B-Instruct2025.106262
Min-K%++Target Model=DeepSeek-Math-7B-Instruct2025.106249
CDDTarget Model=Qwen2.5-7B-Instruct2025.105747
PPLTarget Model=Qwen2.5-7B-Instruct2025.105450
Min-K%Target Model=Qwen2.5-7B-Instruct2025.103250
Min-K%++Target Model=Qwen2.5-7B-Instruct2025.10031