AI Detection Score Meaning

What does the Originality.ai’s AI detector score mean? Learn what the score means and how to use the results. 

These are the questions we’ll answer:

• What is the AI Detection Score
• Is the Score Accurate?
• ‍Is the Score Perfect?
• What if an AI Detector Thinks Something I Wrote was AI-Generated? This is called a False Positive
• Which Model Should I Use?
• Should Plagiarism Checking and AI Detection be Treated the Same?
• How Does Our AI Detector Work?
• What Part is AI? Why Was My Articles Identified As AI?

What is the AI Detection Score?

Our AI detector provides a probability that a piece of content was AI or Original (human-generated). It returns a confidence score. 

‍60% Original and 40% AI means the model thinks the content is Original (human-written) and is 60% confident in its prediction. 

‍This score DOES NOT mean that 60% of it was Original and 40% was AI-generated. 

If you wrote 100% of the copy yourself and you receive a 60% Original score that is not a false positive. Originality.ai’s AI detector has correctly predicted the content was human-generated with 60% confidence.  

Is the Score Accurate?

Yes, the detector has demonstrated accuracy in both internal tests and multiple 3rd party studies. 

• Our Internal Accuracy Study
• Six 3rd Party Studies (identifying Originality.ai as the most accurate)

Is the Score Perfect?

No, the tool does produce incorrect predictions. Incorrectly predicting content that was human generated as AI generated happens approximately 1% of the time. 

What if an AI Detector Thinks Something I Wrote was AI-Generated? This is called a False Positive.

False positives are painful when they occur, and we are working hard to continually improve and release even better models that drive down our false positive rate further. 

A false positive occurs when an AI detector thinks something was AI-generated when in fact it was written by a human. 

We have a free Chrome extension to assist in transparently showing you the writing process that truly created it (whether human-written or AI-generated).

We also have guidance on how to prevent and deal with false positives.

• How to Prevent False Positives
• How to Deal with Accusations of Using AI

Which Model Should I Use? 

Originality.ai provides distinct models that are tuned to meet the needs of specific use cases. 

The AI detection models that are currently available include: 

• Litesome text
  • 98% accurate at detecting AI content
  • Under 1% false positive rate
  • Allows for some light AI editing
• Standardsome text
  • 99%+ accurate at detecting AI content
  • Under 2% false positive rate
  • Allows for some light AI editing
• Turbosome text
  • 99%+ accurate at detecting AI content
  • Under 5% false positive rate
  • Robust against bypassing methods
  • Does not allow for AI editing

Read more about each model here

Should Plagiarism Checking and AI Detection Be Treated the Same?

The answer is no. A Plagiarism Checker provides hard proof that plagiarism occurred, while an AI Detector provides the probability that a piece of content was AI or human-generated. The same approach should not be taken with Plagiarism and AI detection.

How Does Our AI Detector Work?

Our AI takes a more holistic and far more intensive approach to analyze an article to determine if it was AI-generated than anything else we have seen.

Read our in-depth article, How Does AI Content Detection Work?, to learn more about our AI detection tool. Our AI was trained on an incredible number of the most popular LLMs including ChatGPT, Claude, and Llama, and is able to accurately identify patterns in AI content across an entire article. 

Our approach is a far more intensive/accurate way to look at an article than the free AI detection tools that rely on either…

1. A linear probabilistic model — These tools use OpenAI’s model to predict what the next word would be based on the NLP model. If enough of the next words in a piece of content fit within what the model would predict then it is likely AI. This is easy to fool with the changing of a few words.
2. “Burstiness” and “Perplexity” — These tools rely on the fact that AI content is typically consistently created without much variation. They are susceptible to being tricked, which can result in many false positives.

What Part Is AI? Why Was My Articles Identified As AI?

We appreciate the valid question, “Why was my article identified as AI?”

In order to help answer that question, we provide sentence-level highlighting showing what parts the Originality AI Detector believes are more likely to be AI-generated. 

Note: The patterns that our AI picks up on cannot be translated into a simple list of ‘here are x reasons why your content is identified as AI-generated’.