At a target false positive rate of 1%, OpenAI says its detector identified watermarks in about 80% of 200-token passages, compared with about 95% of 400-token passages, for content such as psychology, with substantially lower rates for content such as mathematics.

The exact words it rests on

At a target false positive rate of 1%, our detector identified watermarks in about 80% of 200-token passages, compared with about 95% of 400-token passages, for content such as psychology. Detection rates were substantially lower for content such as mathematics, where there is less flexibility in word choice.

What the source said when we opened it, on 6 Oct 2026.

The source

Our approach to EU text provenance rules
OpenAI · 2026-10-05

Open the sourcearchived copy

Checked

Checked by the notis newsroom on 6 Oct 2026, against the source above.

The number in it

• 80% · textGrain, benchmark score (Watermark detection, 200-token passages, 1% false positive rate, content such as psychology)
• 95% · textGrain, benchmark score (Watermark detection, 400-token passages, 1% false positive rate, content such as psychology)

In the story

OpenAI will watermark ChatGPT and Codex text in the EU 6 Oct 2026