Researchers have developed GAMUT, a new benchmark designed to evaluate the factual completeness of long-form AI-generated text. Unlike previous methods that focused on the accuracy of individual claims, GAMUT assesses whether a response includes all necessary information, addressing the 'missing half of factuality.' The benchmark utilizes a two-level meta-rubric system that can be mechanically compiled into machine-gradable checklists, proving effective even with LLM judges. In evaluations, GAMUT presented a significant challenge to 14 frontier and open-weight models, with Google's Gemini 3.1 Pro achieving the highest score of 58.7%. AI
IMPACT This benchmark could drive improvements in AI's ability to generate comprehensive and factually complete long-form content.
RANK_REASON The cluster describes a new academic paper introducing a benchmark for evaluating AI model outputs.
AI-generated summary · Google Gemini · from 3 sources. How we write summaries →
