List your company

Data Leakage Detection on APPS

81.91AccuracySrDetection
44.78254.42164.0673.699Jun 29, 2026

Evaluation results

MethodLinks
SrDetectionBase Model=Qwen2.5-7B, Training Epochs=52026.0681.9181.8982.2781.85
SrDetectionBase Model=LLaMA3.1-8B, Training Epochs=52026.0678.679.0278.5878.51
SrDetectionBase Model=Qwen2.5-7B, Training Epochs=32026.0666.2466.2866.7866
SrDetectionBase Model=LLaMA3.1-8B, Training Epochs=32026.0663.0663.4563.0962.82
SrDetectionBase Model=Qwen2.5-7B, Training Epochs=12026.0654.6454.7355.5153.02
VeilProbeBase Model=Qwen2.5-7B, Training Epochs=52026.0651.7551.8351.6950.78
VeilProbeBase Model=LLaMA3.1-8B, Training Epochs=52026.0651.6151.6451.6351.53
SrDetectionBase Model=LLaMA3.1-8B, Training Epochs=12026.0651.595251.6849.58
VeilProbeBase Model=LLaMA3.1-8B, Training Epochs=12026.0651.5651.651.5851.48
VeilProbeBase Model=LLaMA3.1-8B, Training Epochs=32026.0651.2751.2851.2851.25
VeilProbeBase Model=Qwen2.5-7B, Training Epochs=12026.0651.0451.150.9649.33
VeilProbeBase Model=Qwen2.5-7B, Training Epochs=32026.0650.9550.9350.9150.68
DPDLLMBase Model=LLaMA3.1-8B, Training Epochs=32026.0650.3450.2899.9533.88
DPDLLMBase Model=Qwen2.5-7B, Training Epochs=32026.0650.2850.2698.6834.84
DPDLLMBase Model=LLaMA3.1-8B, Training Epochs=12026.0650.2350.2310033.59
DPDLLMBase Model=Qwen2.5-7B, Training Epochs=12026.0649.6249.4211.9741.22
DPDLLMBase Model=LLaMA3.1-8B, Training Epochs=52026.0649.0749.6495.3534.99
DPDLLMBase Model=Qwen2.5-7B, Training Epochs=52026.0646.2147.7273.8941.7