Flaws in the LLM Automation Narrative
2026-06-09 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors compared a top language model to human experts on a task that involved writing computer code for data analysis. They found that while language models perform well on average, human experts did better overall and made fewer mistakes. The study also showed that language models' performance is less consistent and their errors can be larger. The authors highlight that it's important to check not just average scores but also how reliable and accurate the results are, especially for important decisions.
Large Language ModelsBenchmarkingHuman ExpertsData AnalysisPerformance VarianceError MagnitudeComputer CodeStandardized Datasets
Authors
George Perrett, Javae Elliott, Jennifer Hill, Marc Scott
Abstract
Large Language Models (LLMs) are increasingly described as performing at the level of human experts on knowledge economy tasks. These claims are primarily based on how LLMs perform on benchmarking tasks that measure average performance across standardized datasets. Primary limitations of many benchmarking tasks are that they often measure performance based on content directly included in LLM training data, and they frequently do not assess the reliability of LLM performance or the magnitude of LLM errors. However, in high stakes contexts, these qualities are critically important. Through a novel LLM benchmarking task that requires writing computer code to complete a data analysis task, we compare the performance of a frontier LLM against submissions from human experts and explicitly measure the variance of responses and the magnitude of errors. Our study reveals that the human experts perform better on average on a range of metrics and demonstrate less variability in performance. Our results provide evidence that LLMs do not consistently perform at the level of human experts and demonstrate the importance of measuring variance and assessing error magnitude in LLM benchmark evaluations.