Is TOON a Good Format for Passing Table Data to LLMs?
Results from testing how well an LLM understands tabular data in Token-Oriented Object Notation (TOON) compared to other formats.
Practical strategies and proven techniques for building better AI agents
Join top practitioners getting actionable AI agent insights
We respect your privacy. Unsubscribe at any time.
Results from testing how well an LLM understands tabular data in Token-Oriented Object Notation (TOON) compared to other formats.
Results from tests looking at how well LLMs understand Token-Oriented Object Notation (TOON) compared to better-known formats such as JSON and XML.
We tested LLMs from three different providers on nested data in JSON, YAML, XML, and Markdown formats. Two models performed best with YAML, while Markdown was the most token-efficient format.
We benchmarked 11 data formats, including markdown tables, JSON, CSV, YAML, XML, and more, to see which LLMs understand best. We found surprising accuracy and token cost trade-offs.