Alpha Excel Benchmark

TL;DR

This paper introduces a new benchmark for evaluating Large Language Models using Excel challenges from the Financial Modeling World Cup, highlighting their strengths and weaknesses in practical business tasks.

Contribution

It converts FMWC challenges into a standardized JSON format and provides a comparative analysis of LLM performance on these real-world tasks.

Findings

Models excel in pattern recognition tasks.

Models struggle with complex numerical reasoning.

Performance varies significantly across challenge categories.

Abstract

This study presents a novel benchmark for evaluating Large Language Models (LLMs) using challenges derived from the Financial Modeling World Cup (FMWC) Excel competitions. We introduce a methodology for converting 113 existing FMWC challenges into programmatically evaluable JSON formats and use this dataset to compare the performance of several leading LLMs. Our findings demonstrate significant variations in performance across different challenge categories, with models showing specific strengths in pattern recognition tasks but struggling with complex numerical reasoning. The benchmark provides a standardized framework for assessing LLM capabilities in realistic business-oriented tasks rather than abstract academic problems. This research contributes to the growing field of AI benchmarking by establishing proficiency among the 1.5 billion people who daily use Microsoft Excel as a meaningful evaluation metric that bridges the gap between academic AI benchmarks and practical business applications.