In March, a study was published on various generative AI platforms to determine the best option. With recent advancements in the field, including OpenAI’s ChatGPT introducing plugins, Google’s Bard enhanced by Gemini, and Anthropic’s development of Claude, a decision was made to revisit the study with additional test queries and a revised evaluation approach.
The study compared platforms such as Bard, Bing Chat Balanced, Bing Chat Creative, ChatGPT (based on GPT-4), and Claude Pro. SGE was excluded due to inconsistent responses. The analysis focused on asking 44 different questions across various categories to gauge user experience.
Bard/Gemini emerged as the top performer overall, excelling in local search queries. Bing Chat lagged due to accuracy issues but stood out in providing citations and additional resources. ChatGPT faced challenges with current events and web access but improved significantly with the MixerBox WebSearchG plugin.
Claude showed promise in generating article outlines and handling certain queries well. Each platform’s strengths and weaknesses were highlighted across categories like article creation, bio queries, commercial queries, disambiguation, jokes, medical queries, article outlines, local queries, and content gap analysis.
The scoring system assessed metrics like relevance, accuracy, completeness, quality, and resources, with Bard leading in understanding searcher intent. Bing Chat excelled in providing citations, while ChatGPT and Claude faced limitations without live webpage access. The study emphasized the evolving landscape of generative AI technology and the potential for further advancements.
The comprehensive evaluation showcased the varying capabilities of each platform, emphasizing the importance of context, accuracy, and user intent in determining the best generative AI solution for different use cases.
