Pangram 称其新 AI 文本检测器每 24,000 份文档仅犯一次错误

Pangram has released Pangram 4, a new model for detecting AI-generated text. The model is six times larger than its predecessor, with 14 times fewer false positives and six times fewer missed AI texts. In the company's own benchmarks, it correctly identifies 99.66 percent of all AI text and falsely flags human writing just 0.0041 percent of the time, roughly one error per 24,000 documents. Pangram 4 can also distinguish lightly AI-polished text from fully AI-generated text, the company says. It resists "humanizer" tools that disguise AI writing as human, catching the AI component across 13 common humanizers 98.83 percent of the time. The API costs $0.05 per 100 words, a two- to tenfold price increase depending on document length. All plans now include image scanning at no extra cost. Pangram 3 stays available until September 30, 2026. Business is booming, according to the New York Times . Annual revenue has grown 35x year over year, and monthly users jumped from 2,700 in June 2025 to 120,000 in June 2026. Ad DEC_D_Incontent-1 Ad Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.