---
id: AGI-DEF-001
title: "Definitions and Operational Criteria for AGI"
alternative_names:
  - "Defining AGI"
  - "AGI Operational Definitions"
category: "Advanced Intelligence → General Intelligence"
volume: V
chapter: 26
entry_type: "Technical Article"
level: 4
status: "Draft"
last_reviewed: 2026-10-15
version: "0.1.0"
prerequisites:
  - "AGI-001"
  - "FOUND-002"
related_entries:
  - "AGI-REQ-001"
  - "AGI-TEST-001"
  - "AGI-TIME-001"
  - "ASI-DEF-001"
  - "CAP-BENCH-001"
---

# Definitions and Operational Criteria for AGI

## 1. Concise Definition
This article surveys the competing definitions of **artificial general intelligence (AGI)** and the operational criteria that have been proposed to decide when a system satisfies one of them. There is no single accepted definition: published definitions differ in whether they specify an economic outcome, a distribution over tasks, a human reference class, or a formal mathematical measure, and these choices change which systems qualify and when forecasters expect the threshold to be met.

## 2. Overview & Significance
The term AGI is used in research papers, corporate mission statements, contracts, safety policies and public forecasting. [AGI-001](../vol05_agi/AGI-001_artificial_general_intelligence.md) introduces the concept; this article is concerned with a narrower question, namely what it would mean to say that a given system *is* an AGI, and how that claim could be checked.

The question has practical weight. A forecast of "AGI by year X" is a forecast about a particular definition, so two forecasts that use different definitions are not comparable. Survey results illustrate the dependence: the 2023 survey of Grace et al. (2025, arXiv version 2024) reported that the aggregate forecast gave a 10% chance by 2027 and a 50% chance by 2047 of "unaided machines outperforming humans in every possible task", whereas the aggregate forecast for "all human occupations becoming fully automatable" was 10% by 2037 and 50% by 2116 (survey conducted in 2023; 2,778 respondents). The two questions describe different thresholds, and the figures are 69 years apart at the 50% level. Definitions also appear in governance: safety frameworks and corporate agreements that refer to AGI inherit whatever ambiguity the underlying definition carries.

## 3. Historical Development
The phrase "general intelligence" predates computing. Goertzel and Pennachin (2007) collected research programmes under the label AGI to distinguish work on broad, flexible intelligence from the specialised systems that dominated applied AI. Legg and Hutter (2007a) collected informal definitions of intelligence from psychology and AI and distilled them into a single informal statement; in a companion paper (Legg & Hutter, 2007b) they gave a formal definition, discussed in Section 4.

Informal operational proposals preceded both. Turing (1950) proposed replacing the question whether machines can think with an imitation game, a behavioural criterion that is still discussed as an early operational test (see [AGI-TEST-001](../vol05_agi/AGI-TEST-001_testing_claims_of_general_intelligence.md)). Later definitions reflect different priorities: formal definitions (Legg & Hutter, 2007b), skill-acquisition definitions (Chollet, 2019), a taxonomy-based definition (Morris et al., 2024) and a cognitive-profile definition (Hendrycks et al., 2025). Claims that early systems showed signs of general intelligence (Bubeck et al., 2023) prompted renewed debate about what evidence such claims require.

## 4. Technical / Conceptual Explanation

### 4.1 Families of definition
The definitions in current use fall into five groups. The groups overlap, and a given author may combine several.

1. **Economic or outcome definitions.** These define AGI by what it can do in the economy. The OpenAI Charter describes AGI as "highly autonomous systems that outperform humans at most economically valuable work" (OpenAI, n.d.). The definition is operational in principle, since it can be checked against labour-market tasks, but it depends on how "most", "outperform" and "economically valuable" are measured, and on the cost at which the work is done.
2. **Formal, environment-distribution definitions.** Legg and Hutter (2007b) define the *universal intelligence* of an agent $\pi$ as its expected performance over all computable environments, weighted by simplicity:
$$\Upsilon(\pi) = \sum_{\mu \in E} 2^{-K(\mu)} V_\mu^\pi$$
where $E$ is the set of computable reward-bearing environments, $K(\mu)$ is the Kolmogorov complexity of environment $\mu$, and $V_\mu^\pi$ is the expected total reward of $\pi$ in $\mu$. This is a mathematical definition and is Established as such. It is not directly usable as a test: $K$ is not computable, and the result depends on the choice of reference machine, so it does not by itself identify a threshold for "general".
3. **Skill-acquisition definitions.** Chollet (2019) argues that intelligence should be defined as skill-acquisition efficiency over a scope of tasks, relative to priors and experience, and that measuring skill alone conflates intelligence with prior knowledge or training data. On this view a benchmark score is evidence of generality only when the system could not have been prepared for the tasks.
4. **Tiered capability taxonomies.** Morris et al. (2024) propose a matrix with two axes, performance and generality, instead of a single threshold. Their performance levels are Emerging (equal to or somewhat better than an unskilled human), Competent (at least the 50th percentile of skilled adults), Expert (90th), Exceptional (99th; called "Virtuoso" in earlier versions of the preprint) and Superhuman (outperforms 100% of humans). The paper states six principles for a definition: focus on capabilities rather than processes; on generality and performance; on cognitive and metacognitive rather than physical tasks; on potential rather than deployment; on ecological validity; and on the path to AGI rather than a single endpoint. As of the paper's assessment, dated September 2023 in the paper, the authors classified then-current frontier language models as Emerging general AI. That classification is the authors' own judgement, not a measurement protocol applied by an independent party.
5. **Cognitive-profile definitions.** Hendrycks et al. (2025) define AGI as "matching the cognitive versatility and proficiency of a well-educated adult", split general intelligence into ten core cognitive domains, and report domain-level scores for named models (the abstract gives GPT-4 at 27% and GPT-5 at 57%). The scores come from the authors' own scoring scheme and are Preliminary: they await independent replication, and the framework's weights and test selection are choices that other authors might make differently.

### 4.2 What an operational criterion must fix
A definition becomes operational only when it specifies the following. Where a published definition leaves an item open, claims made under it cannot be falsified.

- **Reference class**: unskilled humans, skilled adults, domain experts, or the best human at each task.
- **Task distribution**: finite fixed battery, open-ended sampling, or the economy's tasks. Fixed batteries are vulnerable to contamination and to optimisation against the benchmark (see [CAP-BENCH-001](../vol04_capabilities/CAP-BENCH-001_ai_evaluation.md)).
- **Aggregation**: whether superhuman performance on some tasks compensates for failure on others. Morris et al. (2024) require breadth and depth jointly; the economic definition aggregates by value.
- **Cost and autonomy**: whether the system must act without human help and at what cost, which matters for the "autonomous" element in the Charter wording.
- **Access conditions**: tools, retrieval, scaffolding, and time allowed per task.
- **Prior exposure**: whether tasks may appear in training data. This is the core of the Chollet (2019) critique.

### 4.3 Relationship between definitions
A system can satisfy one definition and fail another. A system that outperforms most humans on a fixed academic battery may not perform most paid work autonomously, and a system able to do paid digital work may not satisfy a physical-task criterion. Because definitions differ in strength, the term "AGI" without a stated definition should be read as underspecified.

## 5. Types, Components & Classifications
The table classifies representative definitions by their operational character. It records the form of each definition, not a judgement of its merit.

| Source | Family | Threshold | Operationalised by | Main open issue |
| :--- | :--- | :--- | :--- | :--- |
| OpenAI Charter | Economic outcome | "outperform humans at most economically valuable work" | Not specified in the text | Measuring "most" and "economically valuable" |
| Legg & Hutter (2007b) | Formal | Maximal $\Upsilon$ (no threshold) | Mathematical definition | Non-computable; reference-machine dependence |
| Chollet (2019) | Skill acquisition | Efficiency relative to priors and experience | Proposed benchmark design (ARC) | Quantifying priors and experience |
| Morris et al. (2024) | Tiered taxonomy | Percentile of skilled adults at each level | Matrix of performance by generality | Selecting the task set that defines "general" |
| Hendrycks et al. (2025) | Cognitive profile | "well-educated adult" versatility | Ten-domain scoring scheme | Choice and weighting of domains |

Two further distinctions recur. *Strong* versus *weak* AI, in the philosophical sense, concerns whether a system has a mind; it is distinct from the capability-based senses above and is treated in [FOUND-005](../vol01_foundations/FOUND-005_philosophy_of_mind.md). *Human-level* versus *human-like* contrasts matching performance with matching mechanism, a distinction Morris et al. (2024) make explicit by focusing on capabilities rather than processes.

## 6. Applications & Concrete Examples
Definitions are used in several places, and each use applies its own criterion.

- **Forecasting surveys.** Grace et al. (2025) asked about two differently worded thresholds, as described in Section 2; the difference between the two answers is a direct measure of how much the wording matters. See [AGI-TIME-001](../vol05_agi/AGI-TIME-001_agi_forecasting.md).
- **Evaluation design.** ARC-AGI-2 (Chollet et al., 2025) was released as a successor to a benchmark introduced in 2019 because the authors judged that recent progress required "finer-grained evaluation at higher levels of cognitive complexity." This illustrates a definition (skill acquisition on novel tasks) driving a concrete instrument. The details of such instruments are covered in [AGI-TEST-001](../vol05_agi/AGI-TEST-001_testing_claims_of_general_intelligence.md).
- **Organisational policy.** Frontier developers refer to AGI in mission statements and in capability thresholds for safety frameworks. The wording of such documents changes over time and is outside the scope of a stable article; current versions should be read directly.
- **Case studies of claimed generality.** Bubeck et al. (2023) described early experiments with GPT-4 as showing "sparks" of AGI. Whether it counts as evidence of generality depends on the criterion adopted, which makes it an example of a claim whose status changes with the definition.

## 7. Advantages, Limitations & Unresolved Questions
**Advantages of operational definitions.** They make claims testable, allow forecasts to be compared and resolved, and separate disagreement about the facts from disagreement about words.

**Limitations.**
- Outcome definitions embed economic and institutional factors (regulation, cost, deployment) in what is nominally a capability question. Morris et al. (2024) explicitly avoid this by focusing on potential rather than deployment.
- Formal definitions, such as Legg and Hutter's, are precise but not computable, and the weighting by simplicity is itself a contested assumption.
- Human-relative thresholds depend on the chosen human population. "Skilled adult" is not a fixed standard across tasks.
- Fixed benchmarks can be saturated or contaminated without the system having acquired general skill, which is why Chollet (2019) separates skill from skill acquisition.
- Single-number scoring schemes, such as the percentage scores in Hendrycks et al. (2025), can hide the structure of failure: an agent with a critical deficit in one domain, such as long-term memory storage (which the authors identify), may score well on average.

**Open questions.**
1. Whether any definition can be both formally precise and practically measurable.
2. Whether "general" should be defined over tasks humans do, or over a wider space of tasks. The first is a statement about human-relevant capability; the second is closer to Legg and Hutter.
3. Whether physical competence belongs in the definition. Morris et al. (2024) exclude it from the core criterion; others include embodied tasks.
4. Whether a threshold concept is appropriate at all, or whether a profile of capabilities is more informative. This is Contested.

## 8. Current State of Knowledge
As of 2026-10-15 there is no consensus definition of AGI. No source reviewed for this article shows agreement among researchers on a single operational criterion. The most visible definitions are of the five kinds in Section 4.1, and they are used in parallel. The claim that any existing system meets a given definition is itself definition-dependent: under the Morris et al. (2024) matrix the authors assessed frontier language models as Emerging general AI in 2023; under the Hendrycks et al. (2025) scheme a partial score is reported; under the Charter's wording the answer depends on how economic value is aggregated. Evaluations of this kind are Preliminary. For current model assessments, see the Living Reference collection (`MODEL-001`, `FACT-001`, `TIME-001`) rather than this article.

## 9. Future Trajectory & Strategic Outlook
This section is descriptive; it does not register a forecast.

- **Near term (0 to 3 years).** Definitions are likely to continue to proliferate and to be supplemented by domain-specific capability thresholds (for example, autonomy in software tasks) that avoid the word AGI. The METR time-horizon work (Kwa et al., 2025) is an example of a measurement that sidesteps the definitional question by reporting a single, task-length-based metric.
- **Medium term (3 to 10 years).** Convergence on one definition is not assured. A plausible alternative is convergence on a small set of measurable profiles, but no source reviewed shows evidence for this, and the point is speculative.
- **Long term (10+ years).** If systems exceed human performance on most measured tasks, the weakest definitions will be unambiguously met and discussion will shift towards ASI definitions ([ASI-DEF-001](../vol06_asi/ASI-DEF-001_defining_and_measuring_superintelligence.md)).

No dated forecasts are made here. Registered forecasts are collected in the Forecast Register (`FCST-REG-001`).

## 10. Related Entries & Knowledge Graph
- **Foundational Concepts**:
  - [[AGI-001] Artificial General Intelligence](../vol05_agi/AGI-001_artificial_general_intelligence.md): The overview article; this entry covers definitional detail.
  - [[FOUND-002] Definitions of Intelligence](../vol01_foundations/FOUND-002_definitions_of_intelligence.md): Definitions of intelligence in general, on which AGI definitions build.
  - [[FOUND-005] Philosophy of Mind & The Turing Test](../vol01_foundations/FOUND-005_philosophy_of_mind.md): The imitation game and the strong/weak AI distinction.
- **Related Methods & Technologies**:
  - [[AGI-REQ-001] Requirements for General Intelligence](../vol05_agi/AGI-REQ-001_requirements_for_general_intelligence.md): Which capabilities a definition may require.
  - [[AGI-TEST-001] Testing Claims of General Intelligence](../vol05_agi/AGI-TEST-001_testing_claims_of_general_intelligence.md): How operational criteria are tested.
  - [[CAP-BENCH-001] AI Evaluation, Benchmarking & Contamination](../vol04_capabilities/CAP-BENCH-001_ai_evaluation.md): Benchmark validity.
- **Advanced Implications & Future Trajectories**:
  - [[AGI-TIME-001] AGI Forecasting & Timeline Methodology](../vol05_agi/AGI-TIME-001_agi_forecasting.md): Why definitions determine timelines.
  - [[AGI-PATH-001] Pathways to AGI](../vol05_agi/AGI-PATH-001_pathways_to_agi.md): Routes to systems meeting such definitions.
  - [[ASI-DEF-001] Defining and Measuring Superintelligence](../vol06_asi/ASI-DEF-001_defining_and_measuring_superintelligence.md): The corresponding problem above the human level.

## 11. References & Foundational Literature
1. Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y. T., Li, Y., Lundberg, S., Nori, H., Palangi, H., Ribeiro, M. T., & Zhang, Y. (2023). *Sparks of Artificial General Intelligence: Early experiments with GPT-4*. arXiv preprint. arXiv:2303.12712. [Example of a claim of early general capability that depends on the definition adopted.]
2. Chollet, F. (2019). *On the Measure of Intelligence*. arXiv preprint. arXiv:1911.01547. [Defines intelligence as skill-acquisition efficiency and critiques skill-based measurement.]
3. Chollet, F., Knoop, M., Kamradt, G., Landers, B., & Pinkard, H. (2025). *ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems*. arXiv preprint. arXiv:2505.11831. [Successor benchmark to the 2019 ARC-AGI, introduced for finer-grained evaluation.]
4. Goertzel, B., & Pennachin, C. (Eds.). (2007). *Artificial General Intelligence*. Springer. ISBN: 978-3540237334. [Edited volume associated with the modern AGI label.]
5. Grace, K., Sandkühler, J. F., Stewart, H., Thomas, S., Weinstein-Raun, B., Stein-Perlman, Z., Salvatier, J., Brauner, J., & Korzekwa, R. C. (2025). *Thousands of AI Authors on the Future of AI*. Journal of Artificial Intelligence Research, 84. https://doi.org/10.1613/jair.1.19087 (preprint: arXiv:2401.02843). [Source of the 2,778-respondent survey and the two differently worded thresholds quoted in Section 2.]
6. Hendrycks, D., Song, D., Szegedy, C., Lee, H., Gal, Y., Brynjolfsson, E., et al. (2025). *A Definition of AGI*. arXiv preprint. arXiv:2510.18212 (33 authors). [Cognitive-domain definition of AGI and the abstract's reported scores.]
7. Kwa, T., West, B., Becker, J., Deng, A., Garcia, K., Hasin, M., et al. (2025). *Measuring AI Ability to Complete Long Software Tasks*. NeurIPS 2025; arXiv:2503.14499. [Task-length-based metric as an alternative to a threshold definition.]
8. Legg, S., & Hutter, M. (2007a). *A Collection of Definitions of Intelligence*. Frontiers in Artificial Intelligence and Applications, 157, 17–24. arXiv:0706.3639. [Compiles informal definitions of intelligence.]
9. Legg, S., & Hutter, M. (2007b). *Universal Intelligence: A Definition of Machine Intelligence*. Minds and Machines, 17(4), 391–444. https://doi.org/10.1007/s11023-007-9079-x. [Formal definition of universal intelligence.]
10. Morris, M. R., Sohl-Dickstein, J., Fiedel, N., Warkentin, T., Dafoe, A., Faust, A., Farabet, C., & Legg, S. (2024). *Levels of AGI for Operationalizing Progress on the Path to AGI*. Proceedings of ICML 2024; arXiv:2311.02462. [Performance and generality taxonomy and six defining principles.]
11. OpenAI. (n.d.). *OpenAI Charter*. https://openai.com/charter/. [Source of the economic-outcome wording of AGI; page accessed via search results, publication date not stated on the retrieved text.]
12. Turing, A. M. (1950). *Computing Machinery and Intelligence*. Mind, 59(236), 433–460. https://doi.org/10.1093/mind/LIX.236.433. [Early behavioural criterion for machine intelligence.]

## 12. Evidential Classification Matrix
| Section / Claim | Evidence Category | Supporting Source | Confidence / Status |
| :--- | :--- | :--- | :--- |
| Universal intelligence is a formally defined quantity | Established (mathematical definition) | Legg & Hutter (2007b) | High |
| $\Upsilon$ identifies a practical threshold for AGI | Contested | Legg & Hutter (2007b); Chollet (2019) | Low |
| No single accepted definition of AGI exists | Well Supported (as of this review, from the sources listed) | Morris et al. (2024); Hendrycks et al. (2025); OpenAI (n.d.) | Moderate |
| Survey results depend on wording of the threshold | Well Supported (single survey, quoted figures) | Grace et al. (2025) | High for the quoted figures |
| Frontier models are "Emerging" AGI under the Morris matrix (2023) | Preliminary (authors' own assessment) | Morris et al. (2024) | Moderate |
| Ten-domain scores (GPT-4 27%, GPT-5 57%) | Preliminary | Hendrycks et al. (2025) | Moderate |
| Whether physical tasks belong in the definition | Contested | Morris et al. (2024) | Active debate |

## 13. Revision History
- **v0.1.0** (2026-10-15): Initial draft. Citations checked against arXiv/Crossref/publisher pages where marked; not independently fact-checked.