Artificial General Intelligence (AGI) may become the most significant technological development in human history, yet the term itself remains frustratingly nebulous, acting as a constantly moving goalpost. As specialized AI systems master tasks once thought to require human intellect—from mathematics to art—the criteria for "AGI" continually shift. This ambiguity fuels unproductive debates, hinders discussions about how far AGI is, and ultimately obscures the gap between today's AI and AGI.

This paper provides a comprehensive, quantifiable framework to cut through the ambiguity. Our framework aims to concretely specify the informal definition:

AGI is an AI that can match or exceed the cognitive versatility and proficiency of a well-educated adult.

This definition emphasizes that general intelligence requires not just specialized performance in narrow domains, but the breadth (versatility) and depth (proficiency) of skills that characterize human cognition.

To operationalize this definition, we must look to the only existing example of general intelligence: humans. Human cognition is not a monolithic capability; it is a complex architecture composed of many distinct abilities honed by evolution. These abilities enable our remarkable adaptability and understanding of the world.

To systematically investigate whether AI systems possess this spectrum of abilities, we ground our approach in the Cattell-Horn-Carroll (CHC) theory of cognitive abilities (Carroll, 1993; McGrew, 2009; Schneider and McGrew, 2018; McGrew, 2023; McGrew et al., 2023), the most empirically validated model of human intelligence. CHC theory is primarily derived from the synthesis of over a century of iterative factor analysis of diverse collections of cognitive ability tests. In the late 1990's to 2000's almost all major clinical, individually administered tests of human intelligence have iterated towards test revisions that were either explicitly or implicitly based on CHC model test design blueprints (Keith and Reynolds, 2010; Schneider and McGrew, 2018). CHC theory provides a hierarchical taxonomic map of human cognition. It breaks down general intelligence into distinct broad abilities and numerous narrow abilities (such as induction, associative memory, or spatial scanning). Readers interested in the strengths and limitations of the CHC framework are directed to further scholarly discussions (Wasserman, 2019; Canivez and Youngstrom, 2019).

Decades of psychometric research have yielded a vast battery of tests specifically designed to isolate and measure these distinct cognitive components in individuals. Our framework adapts this methodology for AI evaluation. Instead of relying solely on generalized tasks that might be solved through compensatory strategies, we systematically investigate whether AI systems possess the underlying CHC narrow abilities that humans have. To determine whether an AI has the cognitive versatility and proficiency of a well-educated adult, we test the AI system with the gauntlet of cognitive batteries used to test people. This approach replaces nebulous concepts of intelligence with concrete measurements, resulting in a standardized "AGI Score" (0% to 100%), in which 100% signifies AGI.

The application of this framework is revealing. By testing the fundamental abilities that underpin human cognition—many of which appear simple for humans—we find that contemporary AI systems can solve roughly half of these often-simple assessments. This indicates that despite impressive performance on complex benchmarks, current AI lacks many of the core cognitive capabilities essential for human-like general intelligence. Current AIs are narrower than well-educated humans overall but far smarter on some specific tasks.

The framework comprises ten core cognitive components, derived from CHC broad abilities and weighted equally (10%) to prioritize breadth and cover major areas of cognition:

• General Knowledge (K): The breadth of factual understanding of the world, encompassing commonsense, culture, science, social science, and history.

• Reading and Writing Ability (RW): Proficiency in consuming and producing written language, from basic decoding to complex comprehension, composition, and usage.

• Mathematical Ability (M): The depth of mathematical knowledge and skills across arithmetic, algebra, geometry, probability, and calculus.

• On-the-Spot Reasoning (R): The flexible control of attention to solve novel problems without relying exclusively on previously learned schemas, tested via deduction and induction.

• Working Memory (WM): The ability to maintain and manipulate information in active attention across textual, auditory, and visual modalities.

• Long-Term Memory Storage (MS): The capability to continually learn new information (associative, meaningful, and verbatim).

• Long-Term Memory Retrieval (MR): The fluency and precision of accessing stored knowledge, including the critical ability to avoid confabulation (hallucinations).

• Visual Processing (V): The ability to perceive, analyze, reason about, generate, and scan visual information.

• Auditory Processing (A): The capacity to discriminate, recognize, and work creatively with auditory stimuli, including speech, rhythm, and music.

• Speed (S): The ability to perform simple cognitive tasks quickly, encompassing perceptual speed, reaction times, and processing fluency.

This operationalization provides a holistic and multimodal (text, visual, auditory) assessment, serving as a rigorous diagnostic tool to pinpoint the strengths and profound weaknesses of current AI systems.

Table 1: AGI Score Summary for GPT-4 (2023) and GPT-5 (2025). Model K RW M R WM MS MR V A S Total. GPT-4 8% 6% 4% 0% 2% 0% 4% 0% 0% 3% 27%. GPT-5 9% 10% 10% 7% 4% 0% 4% 4% 6% 3% 57%.

Scope. Our definition is not an automatic evaluation nor a dataset. Rather, it specifies a large collection of well-scoped tasks that test specific cognitive abilities. Whether AIs can solve these tasks can be manually assessed by anyone, and people could supplement their testing using the best evaluations available at the time. This makes our definition more broad and more robust than fixed automatic AI capabilities datasets. Secondly, our definition focuses on capabilities frequently possessed by well-educated individuals, not a superhuman aggregate of all well-educated individuals' combined knowledge and skills. Therefore, our AGI definition is about human-level AI, not economy-level AI; we measure cognitive abilities rather than specialized economically valuable know-how, nor is our measurement a direct predictor of automation or economic diffusion. We leave economic measurements of advanced AI to other work. Last, we deliberately focus on core cognitive capabilities rather than physical abilities such as motor skills or tactile sensing, as we seek to measure the capabilities of the mind rather than the quality of its actuators or sensors. We discuss more limitations in the Discussion.