Skip to main content
Paperresearchv1.0

Emergent Abilities of Large Language Models

by Google Research / Stanford / DeepMind / UNC · free · Last verified 2026-03-17

Defines and documents emergent abilities in LLMs — capabilities that appear sharply at certain model scales rather than improving gradually. Surveys over 100 tasks where models exhibit phase-transition-like capability gains, sparking debate on whether emergence is real or a measurement artifact.

https://arxiv.org/abs/2206.07682
B
BAbove Average
Adoption: AQuality: AFreshness: BCitations: AEngagement: F

Specifications

License
Open Access
Pricing
free
Capabilities
scaling-analysis, capability-evaluation, benchmark-analysis
Integrations
Use Cases
research, capability-forecasting, safety-planning
API Available
No
Tags
emergent-abilities, scaling, phase-transitions, capabilities, benchmark
Added
2026-03-17
Completeness
100%

Index Score

69.6
Adoption
80
Quality
88
Freshness
60
Citations
80
Engagement
0

Put AI to work for your business

Deploy this paper alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.

Explore the full AI ecosystem on Agents as a Service