Last year saw the arrival of ChatGPT with its GPT3, GPT3.5 and GPT4 language models: the conversational artificial intelligence developed by OpenAI.

The availability of ChatGPT to the general public has created a great deal of excitement in many areas, including teaching, training, research, writing, etc.

ChatGPT can generate texts in several languages: French, English, Italian, Spanish, Arabic... A question must be asked to the AI tool to generate these answers.

So how do you know if a content is authentic, written by a human? How to detect AI content? How to detect ChatGPT?

To indicate the nature of an author, several Chat GPT detectors have been developed: they can identify whether a text is generated by an AI (GenAI) such as ChatGPT (GPT-3, GPT-3.5 and GPT4), Gemini (previously Bard), JasperYouChat... or if it is written by a human.

In this article, we identify and compare the best AI detectors for you: 

At the end of the article, you will also find the visual summary of the comparative analysis.

Comparison of best AI detectors  / ChatGPT detectors
what is the best ai detector

When should you ensure the authenticity of the content?

In this context of universal accessibility to AI tools such as ChatGPT (GPT-3, GPT-3.5 and GPT-4) or Gemini; authenticity and originality of content is an issue.

For example, in the fields of education, it is important to ensure that a student's work (homework, essays, dissertations and theses) is original, with properly cited references.

If the teacher cannot ensure the originality of the students' work, he or she cannot ensure that the students have learned their lessons well.

From the student's point of view, the search for ease in writing can sometimes lead to fraudulent practices: plagiarism, ghostwriting by agencies, ghostwriting by an AI...

Behind this ease, the student misses out on the :

  • important knowledge to be acquired according to their specialisation
  • crucial skills to be developed in preparation for professional life: searching for the right sources of information, synthesising, schematising, personal reflection and writing a report.


AI tools can generate texts in abundance. ChatGPT (GPT3, GPT3.5 and GPT4), for example, finds the most likely words to continue an initiated conversation. In most cases, the most likely continuation of a text is the correct answer to the question asked. However, this is not always the case and can contribute to misinformation.

 

Is ChatGPT detectable?

Is ChatGPT detectable?

A frequent concern among users, researchers, teachers and even students is whether ChatGPT and other generative AIs are detectable.

Following various in-depth tests on the detection of content produced by generative AIs, it has been shown that it is statistically possible to identify AI content and therefore to detect texts generated by ChatGPT.

A ChatGPT detector will try to recognize the writing style of the generative AI (GenAI), based on certain subtleties in the texts: context, tone, cultural aspects of the language, etc.

best ai detection for teachers

What software can detect ChatGPT?

Over the past year, several software programs have been developed to detect ChatGPT. These are called :
ChatGPT Detectors or AI Detectors.

Here are the main points to consider when choosing your AI Detector:

  • Software purpose: Some AI detectors have been specially developed for teachers (e.g. Compilatio Magister+). Features are therefore tailored to these users. Other ChatGPT detectors are designed for students or professional editors.
  • Reliability: choose the AI detector you feel is the most reliable, based on the tests and information provided by the developer. Find out more about assessing the reliability of AI detectors: here.

Top 11 best AI detectors compared

 

Focus on our comparison methodology

We conducted an in-depth study to compare the 11 best AI detectors. We tested these ChatGPT detectors with the aim of assessing the reliability of each tool.

We analysed 125 English texts, ranging from 250 to 2500 characters, in the 11 AI Detectors. The texts analysed contain human-written texts, texts generated by ChatGPT and texts generated by YouChat.

The final result of our tests is a reliability rate of analysis for each AI Content Detector, based on the same contents.

Compilatio ChatGPT detector

The Compilatio AI Content Detector (POC*)

 

Presentation of the POC* Compilatio AI Content Detector

  • French company specialised in plagiarism prevention and detection
  • ChatGPT Detector based on GPT2GPT3, GPT3.5, GPT4 and Youchat.
  • Multilingual ChatGPT Detector: French, English, Italian, Spanish, Portuguese, German... 
  • Results displayed as % of reliability and emoji: 🧑 or 🤖.

Results of our tests on the POC* Compilatio AI Content Detector

  • 125 English texts analysed.
  • 46/50 human-written texts recognised, i.e. 92% reliability on human text recognition.
  • 66/75 AI-generated texts recognised, i.e. 88% reliability on the recognition of AI-generated texts.
  • Overall reliability rate: 89.60%.

 

*POC: Proof Of Concept is a project designed to demonstrate the feasibility of a process or an innovation. 
These tests were carried out on the POC in February 2023. Since then, an optimised version of the Compilatio IA detector has been marketed via Compilatio Magister+ (the tests have not been updated).

Draft & Goal ChatGPT detector

Draft & Goal ChatGPT detector

 

Presentation of Draft & Goal ChatGPT detector

  • Canadian company specialised in the development of marketing tools.
  • ChatGPT Detector, based on GPT2 and GPT3.
  • Bilingual ChatGPT Detector: French and English.
  • Results displayed as % of AI content in text.

Results of our tests on Draft & Goal ChatGPT detector

  • 118 English texts analysed.
  • 43/50 human-written texts recognised, i.e. 86% reliability on human text recognition.
  • 59/68 AI-generated texts recognised, i.e. 86.76% reliability on the recognition of AI-generated texts.
  • Overall reliability rate: 86.44%.
GLTR Test-2 ChatGPT Detector

GLTR Test-2 (Giant Language model Test Room): ChatGPT Detector

 

Presentation of GLTR Test-2: ChatGPT detector

  • ChatGPT Detector developed by researchers at MIT-IBM Watson AI lab and Harvard NLP.
  • ChatGPT Detector, based on GPT2.
  • No information provided on the languages processed by this AI Checker.
  • Results are displayed as different colours for each word according to the probability of the AI predicting the word.

Results of our tests on GLTR Test-2: ChatGPT detector

  • 125 English texts analysed.
  • 49/50 human-written texts recognised, i.e. 98% reliability on the recognition of human texts.
  • 55/75 AI-generated texts recognised, i.e. 73.33% reliability on the recognition of AI-generated texts.
  • Overall reliability rate: 83.20%.
gptzero Chatgpt detector

GPTZero - AI Detector

 

Presentation of GPTZero - AI Detector

  • AI Detector created by Edward Tian, a 22-year-old student at Princeton University (USA).
  • AI Detector, based on the GPT-3 model.
  • No information provided on the languages processed by this AI Detector.
  • Results are displayed as a final rating: human or AI text.

Results of our tests on GPTZero - AI Detector

  • 125 English texts analysed.
  • 42/50 human-written texts recognised, i.e. 84% reliability on the recognition of human texts.
  • 59/75 AI-generated texts recognised, i.e. 78.67% reliability on the recognition of AI-generated texts.
  • Overall reliability rate: 80.80%.
Content at Scale AI Detector : chat gpt 3 detector

Content at Scale - AI Text Detector

 

Presentation of Content at Scale - AI Text Detector

  • Company specialised in the development of marketing solutions.
  • ChatGPT Detector, based on GPT-3.
  • No information provided on languages processed by this AI Content Detector.
  • Display of results as % of AI and Human content.

Results of our tests on the AI detector of Content at Scale

  • 125 English texts analysed.
  • 43/50 human-generated texts recognised, i.e. 86% reliability on human text recognition.
  • 57/75 AI-generated texts recognised, i.e. 76% reliability on the recognition of AI-generated texts.
  • Overall reliability rate: 80%.
detectgpt from sokat ai detector

DetectGPT from Sokat

 

Presentation of DetectGPT from Sokat

  • American company specialised in the development of AI solutions.
  • No information on the detected artificial intelligences by this AI Content Detector.
  • No information on the languages processed by this Chat GPT Detector.
  • Results displayed as % of AI content.

Results of our tests on DetectGPT from Sokat

  • 123 English texts analysed.
  • 49/50 human-written texts recognised, i.e. 98% reliability on human text recognition.
  • 46/75 AI-generated texts recognised, i.e. 61.33% reliability on the recognition of AI-generated texts.
  • Overall reliability rate: 77.24%.
crossplag Chatgpt detector

Crossplag ChatGPT detector

 

Presentation of Crossplag ChatGPT detector

  • American company specialising in similarity detection.
  • No information communicated on the detected Artificial Intelligences by this AI Checker.
  • ChatGPT Detector for English texts only.
  • Results displayed as % of AI content.

Results of our tests on Crossplag ChatGPT detector

  • 125 English texts analysed.
  • 43/50 human-written texts recognised, i.e. 86% reliability on human text recognition.
  • 52/75 AI-generated texts recognised, i.e. 69.33% reliability on the recognition of AI-generated texts.
  • Overall reliability rate: 76.61%.
kazan seo ChatGPT Detector

Kazan SEO - ChatGPT Detector

 

Presentation of Kazan SEO - ChatGPT Detector

  • Company specialised in the development of tools to help optimize the natural referencing of websites.
  • No information on the artificial intelligences detected by this AI Checker.
  • No information on the languages processed by this AI Writing Detector.
  • Results displayed as % of real or artificial text.

Results of our tests on Kazan SEO - ChatGPT Detector

  • 124 English texts analysed.
  • 40/50 human-generated texts recognised, i.e. 80% reliability on human text recognition.
  • 52/75 AI-generated texts recognised, i.e. 69.33% reliability on the recognition of AI-generated texts.
  • Overall reliability rate: 74.19%.
AI Text Classifier - Open AI Detector from ChatGPT Developer

AI Text Classifier - Open AI Detector (ChatGPT)

 

Introducing AI Text Classifier - Open AI Detector (ChatGPT)

  • AI Detector developed by Open AI, the company behind ChatGPT.
  • ChatGPT detector, based on GPT2 and GPT3.
  • AI Text Detector in English only.
  • Results are displayed as a rating: AI-generated text very unlikely, unlikely or uncertain.

Results of our tests on AI Text Classifier - Open AI Detector (ChatGPT)

  • 45 English texts analysed.
  • 22/28 human-generated texts recognised, i.e. 78.57% reliability on human text recognition.
  • 11/17 AI-generated texts recognised, i.e. 64.70% reliability on the recognition of AI-generated texts.
  • Overall reliability rate: 73.33%.
Copyleaks AI Content Detector

Copyleaks AI Content Detector

 

Presentation of Copyleaks AI Content Detector

  • American company specialised in the development of similarity detection software.
  • AI Content Detector, based on GPT-2GPT-3 and GPT-4.
  • Multilingual AI Detector: English, French, Spanish, German and Portuguese.
  • Display of results as % of text written by AI or human.


Results of our tests on Copyleaks AI Content Detector

  • 125 English texts analysed.
  • 48/50 human-written texts recognised, i.e. 96% reliability on human text recognition.
  • 42/75 AI-generated texts recognised, i.e. 56% reliability on the recognition of AI-generated texts.
  • Overall reliability rate: 72%.
Writer ChatGPT detector

Writer ChatGPT detector

 

Presentation of Writer ChatGPT detector

  • Company specializ-sed in the development of AI solutions for web editors.
  • No information on the detected artificial intelligences by this ChatGPT Detector.
  • No information on languages processed by this ChatGPT Detector.
  • Results displayed as % of AI and Human content.

Results of our tests on the Writer ChatGPT detector

  • 112 English texts analysed.
  • 39/41 human-written texts recognised, i.e. 95.12% reliability on human text recognition.
  • 38/73 AI-generated texts recognised, i.e. 52.05% reliability on the recognition of AI-generated texts.
  • Overall reliability rate: 68.75%.

Summary of the comparative analysis of the 11 best AI detectors

Here is a graph showing the reliability rates of each AI detector in relation to the number of tests performed:

comparison of the best AI detectors : find the best ai detector
Discover Compilatio AI Checker

In conclusion, the detection of ChatGPT and AI content is possible thanks to AI detectors. Using these tools, you can check whether a text has been written by an AI. Reliability varies according to the ChatGPT detector used.

Identifying the best AI detector depends on a number of factors. It's up to you to find the best AI detector/ChatGPT detector to suit your needs.

 

Also, we would like to remind you that artificial intelligence is part of our lives and that we need to adapt to this change, to learn to work with these tools. 

In education, for example, artificial intelligence can be useful to : 

  • improve the understanding of concepts by providing clear and concise explanations with concrete examples 
  • create interactive exercises that help students learn in a fun way
  • ... 

On the other hand, it remains important for all of us to check for AI and detect ChatGPT or other GenAI. 

 


To go further :