Is GPT-5.1 Content Detectable?

OpenAI released GPT-5.1 on November 12, 2025. OpenAI’s announcement highlights that GPT-5.1 is “A smarter, more conversational ChatGPT.”

This latest version of ChatGPT follows a number of 2025 model releases from OpenAI, including GPT-5 and GPT-4.5.

But is GPT-5.1-generated text still detectable? In this study, we analyzed whether GPT-5.1 content is still identified as Likely AI by the industry-leading Originality.ai AI Checker.

The Quick Answer — Is GPT-5.1 Text Detectable?

Yes, with the release of GPT-5.1, Originality.ai is still highly accurate across all models: Lite 96%, Turbo 98%, and Academic 96%.

The GPT-5.1 Detectability Study

LLMs, like ChatGPT from OpenAI, are continuously improving — at Originality.ai, we believe that it’s essential for AI detectors to continue testing their accuracy on the latest LLM releases.

Our commitment to continuous testing and improving AI detection accuracy is why Originality.ai is the most accurate AI detector.

So, when OpenAI released GPT-5.1, we set out to test the accuracy of our AI detection models on the latest from OpenAI.

The GPT-5.1 Detectability Test

Although our AI detection models were not trained on GPT-5.1 data, this study assesses their capability to identify text generated by GPT-5.1.

The Dataset:

5,000 high-quality human-written samples spanning:

• Domains/Topics: health, news, finance, technology, arts & entertainment
• Content Types: blogs, reviews, expository articles, conversational text
• Prompt Structures: to maximize stylistic and topical diversity

Then, GPT-5.1 was used to generate completions for each human-written sample prompt. 

This produced a balanced dataset to evaluate the accuracy of Originality.ai’s AI detection capabilities.

The GPT-5.1 Detectability Results

After testing the Originality.ai AI detection models on this dataset, we found that GPT-5.1 is still detectable by the industry-leading Originality.ai AI detector with a high degree of accuracy.

These are the accuracy ratings for GPT-5.1 by Originality.ai AI detection models:

‍

Final Thoughts

Even though GPT-5.1 did not yet exist during training for our AI detection models, all of our models show a strong generalization performance and achieved an accuracy of 96% to 98%.

So, is Originality.ai still a reliable way to detect GPT-5.1-generated content? Yes!

These results highlight that Originality.ai is still an effective way to detect GPT-5.1-generated content and offers reliable AI detection for writers, editors, students, teachers, and more.

Try Originality.ai’s AI detector today!

Learn more about AI detection accuracy:

• AI Detection Accuracy Study
• 3rd Party AI Detection Accuracy Studies: Meta-Analysis
• Which AI Detection Model Should I Use?
• Originality.ai’s Academic Model for Students and Teachers