Pangram says its AI detector hits 99.98% accuracy, verified by University of Maryland and University of Chicago
Pangram – AI detector for text and images
Pangram claims 99.98% accuracy in detecting AI-generated text and images, with third-party verification from the University of Maryland and University of Chicago. The tool supports over 20 languages, identifies content from all major LLMs including ChatGPT, Claude, and Gemini, and can even catch "humanized" text. It also offers plagiarism checking, browser extensions, and LMS integrations for schools and enterprises.
AI detection is not magic. It can actually work.
- firefoxd
People expect a binary response, is it AI generated yes or no. But it's more complicated than that. For example, if you see an emdash, it's probably AI generated. But it can also mean the author used it for fixing grammar or tenses. LLMs can't help but try to help. The same for it's not X, but Y. Sure it's a known pattern, but it's not like people don't use this trope all the time.
In my experience, Pangram is great for detecting an author who is trying to pass someone else's work as theirs, or if they are tackling a subject they have little to no knowledge in.
- Codefrontier
Gotta be honest. Pangram is not that reliable. It flagged my texts as 100% human made whilst at best it was 50%.
- jdc-pub
I’m surprised at the current sentiment in the comments. Pangram is amazing and has really interesting engineering too. I would have guessed that reliably identifying LLM generated text was not possible without watermarks.