This study conducts a comprehensive comparative analysis of six contemporary artificial intelligence models for Python code generation using the HumanEval benchmark. The evaluated models include GPT-3.5 Turbo, GPT-4 Omni, Claude 3.5 Sonnet, Claude 3.7 Sonnet, Claude Sonnet 4, and Claude Opus 4. A total of 164 Python programming problems were utilized to assess model performance through a multi-faceted methodology incorporating automated functional correctness evaluation via the Pass@1 metric, cyclomatic complexity analysis, maintainability index calculations, and lines-of-code assessment. The results indicate that Claude Sonnet 4 achieved the highest performance with a success rate of 95.1%, followed closely by Claude Opus 4 at 94.5%. Across all metrics, models developed by Anthropic Claude consistently outperformed those developed by OpenAI GPT by margins exceeding 20%. Statistical analysis further confirmed the existence of significant differences between the model families (p < 0.001). Anthropic Claude models were observed to generate more sophisticated and maintainable solutions with superior syntactic accuracy. In contrast, OpenAI GPT models tended to adopt simpler strategies but exhibited notable limitations in terms of reliability. These findings offer evidence-based insights to guide the selection of AI-powered coding assistants in professional software development contexts.

The SETSCI Conference Proceedings is an Open Access publication created for the storage and indexing of proceedings | The COVID-19 pandemic has necessitated the development of rapid, accurate, and automated diagnostic tools to assist healthcare professionals in patient screening and management. This comprehensive study presents a detailed comparative analysis of ten state-of-the-art Convolutional Neural Network (CNN) architectures for COVID-19 detection using chest X-ray radiography images. The research systematically evaluates DenseNet, ConvNeXTiny, EfficientNetB0, ResNet50, VGG19, VGG16, MobileNet, GoogleNet, AlexNet, and LeNet models using the COVID-19 Radiography Database. Each model was rigorously trained and validated using standardized protocols to ensure fair comparison. Comprehensive performance metrics including validation accuracy, test accuracy, loss functions, convergence analysis, and overfitting assessment were employed. The experimental results demonstrate that modern architectures, particularly DenseNet and ConvNeXTiny, achieved superior performance with 97% validation accuracy and 96% test accuracy, exhibiting excellent generalization capabilities with minimal overfitting (1.00% accuracy difference). The study also analyzes computational efficiency, training dynamics, and practical deployment considerations. These findings provide crucial insights for developing robust computer-aided diagnosis systems for COVID-19 detection and establish benchmarks for future research in medical image classification.