Minerva vs Gopher

Minerva is a large language model from Google Research built to solve math and science questions through step-by-step written reasoning. It reads problems that mix plain English with LaTeX notation, then writes out solutions involving arithmetic, algebra, and symbolic steps. The model was trained on scientific papers and web pages where mathematical formatting was kept intact, rather than stripped during preprocessing.

Most math-capable models lean on external tools like Python interpreters or calculators at inference time. Minerva takes the opposite bet: it generates full worked solutions from the model weights alone, using chain-of-thought prompting and majority voting across multiple sampled answers. That informal approach covers a wider range of problem types than formal theorem provers, but the trade-off is answers cannot be machine-verified the way Coq or Lean proofs can.

Researchers studying quantitative reasoning in language models use Minerva as a reference point for STEM benchmark performance. The public sample explorer hosts 110 solved problems across algebra, physics, chemistry, and other topics, so anyone can read through how the model arrived at each answer. Educators and ML engineers reviewing benchmark methodology will find the published MATH, MMLU-STEM, GSM8k, and OCWCourses scores useful for comparing against newer models.

Discover the cutting-edge advancements in artificial intelligence with DeepMind's exploration of language processing capabilities in AI. At the heart of this exploration is Gopher, a 280-billion-parameter language model designed to understand and generate human-like text. Language serves as the core of human intelligence, enabling us to express thoughts, create memories, and foster understanding.

Realizing its importance, DeepMind's interdisciplinary teams have endeavored to drive the development of language models like Gopher, balancing innovation with ethical considerations and safety. Learn how these language models are advancing AI research by enhancing performance in tasks ranging from reading comprehension to fact-checking while identifying limitations such as logical reasoning challenges. Attention is also given to the potential ethical and social risks associated with large language models, including the propagation of biases and misinformation, and the steps being taken to mitigate these risks.