How We're Making Advanced Scan Highlighting Even More Accurate
A major update helps to make AI results even easier to interpret.
A major update helps to make AI results even easier to interpret.
AI detectors do not always agree, which is exactly why benchmarking matters. In our latest live benchmark, we compared Pangram v3.2, Pangram v3.1, and GPTZero across multiple domains.
GPTZero's analysis 4841 papers accepted by NeurIPS 2025 show there are at least 100 with confirmed hallucinations
GPTZero outperforms other AI detectors like Pangram on Chicago Booth Benchmark, achieving ~99% accuracy and industry-leading recall for AI detection.
GPTZero used our Hallucination Check tool to find 50+ hallucinations under review at ICLR, each of which were missed by 3-5 peer reviewers.
GPTZero confirms its title as the most accurate commercial AI detector, outperforming competitors on the massive independent RAID benchmark.
Here at GPTZero, we’ve just launched our most advanced multilingual model yet. This is what’s new.
GPTZero expands its AI detection coverage of LLMs to DeepSeek’s open-source reasoning model that made waves in the AI industry.
An overview of how AI detectors like GPTZero, TurnitIn, and Copyleaks compare in terms of accuracy rate, error rate, false positives and negatives for identifying AI-generated content.
GPTZero expands its AI detection coverage of LLMs to OpenAI’s latest reasoning models; see our internal benchmarking on how we compare to other AI detectors.