Pangram Image 1.0 detects 99.2% of AI images at 0.27% false positive rate
TuhinChakr · x · 2026-11-05
Pangram launched Pangram Image 1.0, an AI image and video detection model identifying 99.2% of AI-generated images with a 0.27% FPR, integrated into its Chrome extension for checking visuals anywhere on the web. The team describes key challenges: far more AI image/video models than frontier LLMs, more diverse outputs, and the fact that most phone cameras (including iPhones) apply AI postprocessing to real photos — so the model is robust to postprocessing and distinguishes AI edits from fully generated visuals. A new heatmap feature localizes AI artifacts instead of outputting a binary confidence score.
Related event: Pangram launches AI image detector with 99.2% accuracy(3 posts)→
More from Models
- Artificial Analysis details benchmark methodology: every 6 hours, sustained load, agentic sessions — ArtificialAnlys · 2026-11-05
- GLM-5.3's Fastest-Streaming Endpoints Take 18-26s to First Token, Slipping in New Benchmark — ArtificialAnlys · 2026-11-05
- GLM-5.3 endpoint posts 92.8% error rate as Artificial Analysis starts counting failed requests — ArtificialAnlys · 2026-11-05
- Artificial Analysis makes Time per Task its headline metric; default effort cuts task time 3-4x — ArtificialAnlys · 2026-11-05
- Artificial Analysis Overhauls API Benchmarks: Time per Task Replaces Streaming Speed — ArtificialAnlys · 2026-11-05
- Moonshot releases open-weight Kimi K3.1 Pro: 2.8T params, 104B active, 1M context — MaziyarPanahi · 2026-11-05