As large language models (LLMs) become increasingly powerful, traditional evaluation metrics tend to saturate, making it challenging to distinguish between models based on their performance. We propose a general method to transform existing LLM evaluations into a series of progressively more difficult tasks. These enhanced evaluations emphasize reasoning capabilities and can reveal relative performance differences that are not apparent in the original assessments. To demonstrate the effectiveness of our approach, we create a new multiple-choice test corpus, extend it into a family of evaluations, and assess a collection of LLMs. Our results offer insights into the comparative reasoning abilities of these models, particularly highlighting distinctions between OpenAI's o1-preview and Google's gemini-pro-1.5-002.
View on arXiv@article{bradley2025_2411.01533,
title={ Enhancing LLM Evaluations: The Garbling Trick },
author={ William F. Bradley },
journal={arXiv preprint arXiv:2411.01533},
year={ 2025 }
}