{"version":1,"type":"story","url":"https://digestai.news/story/pangram-launches-ai-image-and-video-detectors-with-99-96-accuracy","json":"https://digestai.news/story/pangram-launches-ai-image-and-video-detectors-with-99-96-accuracy.json","markdown":"https://digestai.news/story/pangram-launches-ai-image-and-video-detectors-with-99-96-accuracy.md","slug":"pangram-launches-ai-image-and-video-detectors-with-99-96-accuracy","headline":"Pangram launches AI image and video detectors with 99.96% accuracy","summary":"The flagship model, **Pangram Image 1.0**, achieves **99.96% accuracy** on a test set of 1,200 synthetic images created by 12 frontier AI generators. It includes a **heatmap feature** to pinpoint AI content within images and claims robustness against edits, compression, and low resolutions (now supporting **256x256** pixels with reduced confidence disclaimers below 512x512). The smaller **Flash 1.0** model excels at video detection, scoring **98.7% accuracy** on the **DF26 benchmark**, a **29-point leap** over existing tools. Both models now support **Chrome extensions** for real-time detection on social media and **API access** for developers.\n\nThe company tested its tools against academic benchmarks like **X-AIGD, Mirage-Test, and AIGVDBench**, comparing performance against commercial and open-source detectors. Pangram’s models also support **native video uploads** for frame-by-frame analysis. The release follows a **research preview** earlier this year, with improvements driven by community feedback. Isaac, a research engineer at Pangram (formerly Samsung AI Center NYC), led the development.","keyPoints":["Pangram Image 1.0 achieves **99.96% accuracy** detecting AI-generated images in a test of 1,200 synthetic images","Flash 1.0 scores **98.7% on DF26**, a **29-point improvement** over existing video detectors","Both models now include **Chrome extensions** and **API support**, plus native video upload for frame-by-frame analysis"],"whyItMatters":"These tools could become essential for platforms and users needing to verify image/video authenticity, especially as AI-generated content spreads. The **99.96% accuracy** and **real-time detection** via Chrome extensions address gaps in current detectors, potentially influencing social media, journalism, and e-commerce trust.","category":{"slug":"models","name":"Generative AI & Models","url":"https://digestai.news/category/models"},"entities":{"companies":["Pangram"],"models":["Pangram Image 1.0","Pangram Image Flash 1.0"],"people":["Isaac"]},"firstPublishedAt":"2026-11-04T17:02:08Z","updatedAt":"2026-11-04T17:35:05Z","sourceCount":2,"hasPrimarySource":false,"sources":[{"outlet":"pangram.com","title":"Pangram releases Pangram Image 1.0, which it says is state-of-the-art in AI image and AI video detection, and the smaller Image Flash 1.0 for AI video detection","url":"https://pangram.com/blog/introducing-pangram-image-1-0","publishedAt":"2026-11-04T17:02:08Z","type":"press","primary":false,"lead":true},{"outlet":"Unite.AI","title":"Pangram Launches Two Models for AI Image and Video Detection","url":"https://unite.ai/pangram-launches-two-models-for-ai-image-and-video-detection","publishedAt":"2026-11-04T17:35:05Z","type":"press","primary":false,"lead":false}],"sourceNotes":null,"discussions":[{"site":"Hacker News","url":"https://news.ycombinator.com/item?id=50368458","points":5}],"thread":null,"cite":{"text":"Digest AI, \"Pangram launches AI image and video detectors with 99.96% accuracy\", 4 November 2026, https://digestai.news/story/pangram-launches-ai-image-and-video-detectors-with-99-96-accuracy","publisher":"Digest AI","title":"Pangram launches AI image and video detectors with 99.96% accuracy","datePublished":"2026-11-04T17:02:08Z","url":"https://digestai.news/story/pangram-launches-ai-image-and-video-detectors-with-99-96-accuracy"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}