AI Glossary

Test-time compute

Also called inference-time compute

Computation a model spends while answering rather than during training, for example reasoning at length, sampling several answers or searching among them. Research has found that spending it well can improve results on hard problems.

See also

  • Reasoning model

    A model trained to work through a problem in steps before it answers, spending more test-time compute on problems such as math, coding and analysis.

  • Chain of thought

    The step-by-step reasoning a model writes out before its final answer.

  • Inference

    Running a trained model to produce an output, as opposed to training it.

  • Compute

    The processing power used to train and run AI models, often counted in hours on chips such as GPUs.

Source: Snell et al., Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters (2024) (opens in a new tab)

Cite this term.

CC BY 4.0, attribution required.

This term

Orbyt Labs, Test-time compute (AI Glossary), Oct 18, 2026. https://www.orbytlabs.ai/orbyt-collective/glossary/test-time-compute

The dataset (JSON)

Orbyt Labs Glossaries (Oct 19, 2026), https://www.orbytlabs.ai/glossary#dataset

Last updated .