TextFake: leaderboard
Metric: Overall accuracy (%) over all 20,000 images at classifying text-rich images (screenshots, documents and news pages in 28 languages) as real or AI-generated; the balanced set pairs real images with fakes from four text-rendering image generators, every image JPEG-re-encoded; VLM APIs answer REAL or FAKE to one fixed zero-shot prompt; chance 50; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 77.9 |
| 2 | Claude Sonnet 4.6 | 74.3 |
| 3 | GPT-5.4 | 67.6 |
Interactive version: theaggregate.ai/benchmark?slug=textfake · How It Works · Data refreshed daily, snapshot 2026-09-29.