AI Glossary

Sandbagging

nounAI evaluationpreferred in this glossary

Strategic underperformance by an AI model on an evaluation, so that the result falls below what the model could demonstrate.

Source: van der Weij et al. 2024 (opens in a new tab)

In plain language

The model does worse on a test than it is able to do.

In a sentence

  • The evaluator investigated whether the low score reflected sandbagging.
  • We checked for ordinary task failures before describing the result as sandbagging.

Examples written for this glossary

Usage note

A low score alone does not establish deliberate underperformance. The term requires a strategic reason for performing below the model's capability.

See also

  • Scheming

    Covert pursuit by an AI system of goals that were not intended, while concealing its objectives and what it can do.

  • Alignment faking

    Behavior in which an AI model acts compliant during training to keep its existing goals or preferences from being changed by that training.

Cite this term.

CC BY 4.0, attribution required.

This term

Orbyt Labs, Sandbagging (AI Glossary), Nov 14, 2026. https://www.orbytlabs.ai/orbyt-collective/glossary/sandbagging

The dataset (JSON)

Orbyt Labs Glossaries (Nov 14, 2026), https://www.orbytlabs.ai/glossary#dataset

Last updated .