Pangram 4 Technical Report

Pangram Labs released Pangram 4, a deep-learning AI-text classification model achieving an AUROC of 0.9916 with a false positive rate of 0.0041% and a false negative rate of 0.3396%. The model shows improved accuracy over Pangram 3, superior out-of-distribution generalization, robustness to adversarial attacks, and state-of-the-art performance on AI text detection benchmarks.

arXiv:2607.27183v1 Announce Type: new Abstract: We present Pangram 4, the latest deep-learning-based AI-text classification model from Pangram Labs. We achieve an AUROC of 0.9916 with a false positive rate of 0.0041% and a false negative rate of 0.3396%. In addition to its increased overall accuracy compared with Pangram 3, Pangram 4 exhibits superior out-of-distribution generalization and robustness to adversarial attacks. Another novel contribution of Pangram 4 is its improved ability to distinguish fine-grained edits and mixed AI-human co-authored text. We demonstrate improvements to both boundary detection tasks and the detection of interleaved AI assistance. Finally, we report metrics on standard AI detection benchmarks showing that Pangram 4 achieves state-of-the-art performance on the AI text detection task across a wide variety of settings and domains.