MEME's experiments evaluated its performance against top malware detection systems like Ember, Sorel-LGB, Sorel-FFNN, and Microsoft Defender. The comparison included state-of-the-art techniques like PPO, MAB, and GAMMA, focusing on adversarial malware generation. Constraints on modifications, running time, query budgets, and evaluation metrics standardized the experiments for fair comparison and robust assessment of MEME's efficacy in model evasion.