A Definition of AGI

TL;DR

This paper proposes a quantifiable framework for defining AGI based on human cognitive abilities, revealing current AI models' strengths and critical deficits through empirical assessment aligned with established psychological theories.

Contribution

It introduces a novel, empirically grounded framework for evaluating AGI using human cognitive domains, operationalized through adapted psychometric tools.

Findings

Current AI models show uneven cognitive profiles.

GPT-4 scores 27%, GPT-5 scores 57% on AGI scale.

Significant gaps remain before achieving human-level general intelligence.

Abstract

The lack of a concrete definition for Artificial General Intelligence (AGI) obscures the gap between today's specialized AI and human-level cognition. This paper introduces a quantifiable framework to address this, defining AGI as matching the cognitive versatility and proficiency of a well-educated adult. To operationalize this, we ground our methodology in Cattell-Horn-Carroll theory, the most empirically validated model of human cognition. The framework dissects general intelligence into ten core cognitive domains-including reasoning, memory, and perception-and adapts established human psychometric batteries to evaluate AI systems. Application of this framework reveals a highly "jagged" cognitive profile in contemporary models. While proficient in knowledge-intensive domains, current AI systems have critical deficits in foundational cognitive machinery, particularly long-term memory storage. The resulting AGI scores (e.g., GPT-4 at 27%, GPT-5 at 57%) concretely quantify both rapid progress and the substantial gap remaining before AGI.