# OpenAI RoBERTa detector accuracy on modern AI text

Source: https://toolbenchmarks.com/ai-detectors/openai-roberta/  
Tested: 30 October 2026. Publisher: Tool Benchmarks. Data licence: CC BY 4.0.

> OpenAI's RoBERTa detector caught 9.5% of the AI-written texts in our test and only 2.4% of texts from Claude Opus 5.5. It rarely flags human writing (4.8%), but that is because it calls almost everything human. It was built in 2019 to spot GPT-2 output and does not work on today's models.

Verdict: Obsolete. It almost never flags anything, so a pass from this detector tells you nothing about modern AI text.

| Measure | Result |
|---|---|
| Catches AI text | 9.5% (48 of 504) |
| Flags human text | 4.8% (6 of 126) |
| Catches humanized AI text | 0.0% |
| AUROC | 0.579 |
| Catches Claude Fable 5.1 | 3.2% |
| Catches Claude Haiku 5.5 | 20.6% |
| Catches Claude Opus 5.5 | 2.4% |
| Catches Claude Sonnet 5.5 | 11.9% |
| Flags human text: Academic abstracts | 0.0% |
| Flags human text: Q&A answers | 10.7% |
| Flags human text: Encyclopedia articles | 4.0% |
| Flags human text: Fiction | 4.2% |
| Flags human text: News reports | 4.2% |

## What it is

OpenAI released this RoBERTa-base model in 2019 alongside GPT-2, to show that text from that model could be detected. It is one of the most downloaded detectors on Hugging Face, so people still use it. We used the standard threshold of 0.5.

## Results

It caught 9.5% of AI texts overall. Fiction was its best genre at 25.0%; it caught none of the AI-written forum answers. Not one humanized text was flagged.

Its false positive rate of 4.8% looks good, but a detector that calls almost everything human will always score well on human text. Its AUROC of 0.579 shows how little its scores separate the two.

If you find this detector behind a free online tool, treat a "human" result as meaningless for text written by current chatbots.

## Questions people ask

### Does OpenAI have an AI text detector?

OpenAI released this RoBERTa detector in 2019 for GPT-2 text. It also launched a separate AI text classifier in January 2023 and withdrew it in July 2023 because of its low accuracy. The 2019 model is still downloadable, and it caught 9.5% of AI texts in our test.

### Can the OpenAI RoBERTa detector catch Claude?

Hardly. It caught 2.4% of Claude Opus 5.5 texts, 11.9% of Sonnet 5.5, 20.6% of Haiku 5.5 and 3.2% of Fable 5.1.