# Knowledge Cutoff

> The date a model's training text ends. It knows little after that.

**Field:** Artificial Intelligence  
**Category:** LLMs  
**Also known as:** Training Cutoff, Training Data Cutoff

## Think of it like

Think of it like a letter sealed in a time box. It only knows what was true on the day it was sealed.

## Definition

A knowledge cutoff is the date after which a model's training text stops. The model knows little or nothing about events after it. A model is often released months after its cutoff and used for a year or more beyond that. So it may not know about new products, prices, laws or news. Tools that let the model search the web or read your files fill that gap.

## Example

Emma asks a chat model about a phone launched last month. The model's cutoff was a year ago, so it guesses, or says it does not know.

## Why it matters

Anything new, from prices to laws, may be missing from the model's answer. Or it may be out of date.

## Common mistake

Thinking the model knows today's date or news. Unless a tool gives it the date or a search, it does not.

## Three principles

- **A fixed date.** Training text stops there.
- **Blind after it.** New events are unknown.
- **Search fills the gap.** Fresh sources at question time.

## Related terms

- [Context Window](https://learn.benibix.com/term/ai/context-window)
- [Hallucination (AI)](https://learn.benibix.com/term/ai/hallucination)
- [Pretraining](https://learn.benibix.com/term/ai/pretraining)
- [Training Data](https://learn.benibix.com/term/ai/training-data)

## Told apart from

- [Context Window vs Knowledge Cutoff](https://learn.benibix.com/compare/context-window-vs-knowledge-cutoff): People often think a model with a big context window knows recent news. They are two different limits. The knowledge cutoff is the date its training text stops, so it is about what the model learned. The context window is how much text it can read right now, so it is about what you hand it. Pasting a fresh article into the window is how you get past the cutoff.

## Taught in

- [LLM Hallucinations](https://learn.benibix.com/learn/ai-llms/llm-hallucinations): LLMs, 14/15
- [AI Web Search and Sources](https://learn.benibix.com/learn/ai-use-case/ai-web-search-and-sources): AI Assistants and Chatbots, 3/13

![A timeline. Training text covers the time up to the cutoff date. After it there is a gap, and events in the gap are unknown to the model.](https://learn.benibix.com/diagrams/llm-knowledge-cutoff.svg)

---

Source: https://learn.benibix.com/term/ai/knowledge-cutoff
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-18
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
