List your company

Binary Accuracy on SecGenEval-PS CodeAnalysis

100AccuracyQwen2.5-Coder-7B
38.6454.5770.586.43Jan 10, 2026

Evaluation results

MethodLinks
Qwen2.5-Coder-7BEvaluation Mode=M12026.01100
Qwen2.5-Coder-7BEvaluation Mode=M32026.01100
Qwen2.5-7BEvaluation Mode=M12026.01100
Qwen2.5-Coder-7BEvaluation Mode=M22026.0198.5
GPT-4oEvaluation Mode=M22026.0195.8
GPT-4oEvaluation Mode=M32026.0195.1
o3-miniEvaluation Mode=M22026.0194.4
o3-miniEvaluation Mode=M32026.0189.1
GPT-4oEvaluation Mode=M12026.0187.2
DeepSeek-R1-Distill-Qwen-7BEvaluation Mode=M12026.0157.1
o3-miniEvaluation Mode=M12026.0141