Detection methodology & benchmarks

Headline claims (homepage)

• Detection accuracy: 99.2% detection accuracy based on our internal benchmark of 10,000 human and AI-written text samples. The headline figure (99.2%) is accuracy on a held-out portion of that benchmark after stratified sampling—i.e., how often the ensemble agrees with human-reviewed labels for each document.
• Writers: Used by over 50,000 writers as of March 2026. This reflects cumulative registered product usage, not an academic survey sample.
• Tool count: The public tools hub lists 327 tools (327+ in copy). See All tools.

How detection accuracy is measured

We evaluate the detector on labeled passages and documents where the source is known: human-written text from editorial and public domain samples, and AI-written text from modern LLMs (including GPT-class outputs) generated under controlled prompts. Labels are verified before inclusion in the benchmark.

We report accuracy as the fraction of predictions that match the held-out label at the document level, with additional sentence-level metrics for calibration. Standard mode uses our ensemble stack; DeepScan (paid plans) runs a stronger pass for mixed or edge-heavy content.

Datasets and limitations

The internal benchmark uses roughly 10,000 human and AI-labeled samples combined, with stratified splits so that neither domain nor model family dominates. It is not identical to public leaderboards or third-party test sets.

Real-world performance can differ from benchmark accuracy: very short text, heavy paraphrasing, translated text, or adversarial editing may reduce agreement with labels. For a research-level overview of detector possibilities and limits, see Towards Possibilities & Impossibilities of AI-generated Text Detection: A Survey (arXiv:2310.15264).

Comparison to other tools

We do not publish head-to-head competitor percentages on our private benchmark because vendors use different datasets, label definitions, and thresholds—numbers are rarely comparable without a shared, public test harness. When you see "industry average" claims elsewhere, check which corpus and metric they use.

We focus on transparent methodology: our headline accuracy is tied to the 10k-sample internal benchmark described above. For product decisions, we recommend using the in-app verdict, heatmap, and your editorial judgment together.

Platform metrics (for citations)

• Detection: 99.2% detection accuracy based on our internal benchmark of 10,000 human and AI-written text samples (see sections above).
• Audience scale: Used by over 50,000 writers as of March 2026.
• Languages: Detection and readability are strongest in English; several tools accept other languages with varying degrees of optimization. The Translator supports many language pairs—see the in-app language list for the current set.
• API availability: Production deployments are monitored; Enterprise plans can include SLA terms. Contact sales for uptime commitments specific to your contract.

Questions about this page? See FAQ or About.