This research paper evaluates the performance of DeepSeek, a new large language model (LLM), against other popular models like Claude, Gemini, GPT, and Llama. The comparison focuses on two classification tasks: determining the authorship of text (human or AI-generated) and classifying academic citations based on their function. The study introduces new datasets, MadStatAI and CitaStat, for benchmarking LLMs in these tasks. Results indicate that DeepSeek is competitive, outperforming some models but generally falling short of Claude in accuracy. However, DeepSeek offers a balance of performance and cost-effectiveness, while Claude is more expensive and DeepSeek is comparatively slower. This work highlights the potential of DeepSeek and contributes valuable resources for future LLM research.Source: https://arxiv.org/html/2502.03688v1

Our Sponsors: Certification Ace. A platform to take Cloud Certifications Mock tests for FREE!! Try it today on App Store or Play Store.