Minerva vs GPT-4

Google Research's Minerva project has made significant strides in solving quantitative reasoning problems using language models, showcasing substantial performance improvements in mathematical and scientific tasks. Minerva operates by parsing and processing questions that include mathematical notation and generating step-by-step solutions involving numerical calculations and symbolic manipulation, all without the need for external tools like calculators. Employing techniques such as few-shot prompting, chain of thought prompting, and majority voting, Minerva has achieved state-of-the-art performance on a variety of STEM reasoning tasks. Through its advanced prompting and evaluation methods, Minerva has become an indispensable tool for exploring complex quantitative problems, offering great potential in scientific research and educational applications.

GPT-4 is the latest milestone in OpenAI’s effort in scaling up deep learning.

GPT-4 is a large multimodal model (accepting image and text inputs, emitting text outputs) that, while less capable than humans in many real-world scenarios, exhibits human-level performance on various professional and academic benchmarks. For example, it passes a simulated bar exam with a score around the top 10% of test takers; in contrast, GPT-3.5’s score was around the bottom 10%. We’ve spent 6 months iteratively aligning GPT-4 using lessons from our adversarial testing program as well as ChatGPT, resulting in our best-ever results (though far from perfect) on factuality, steerability, and refusing to go outside of guardrails.

GPT-4 is more creative and collaborative than ever before. It can generate, edit, and iterate with users on creative and technical writing tasks, such as composing songs, writing screenplays, or learning a user’s writing style.