Chaperone-SA-1.0 — drug-level sentiment 473 held-out labels
Sentiment accuracy, same test items for every model
Chaperone-SA-1.091.3%
Qwen3.8-27B83.5%
Qwen3-32B83.3%
MedGemma-27B82.9%
Llama-3.1-8B76.3%

The other models were asked about one drug at a time. Chaperone-SA labels every drug in a document in one request.

91%
sentiment accuracy
84% / 84%
Negative precision / recall
~31 GB
fits on a single NVIDIA L40S
100%
valid labels in 1,500 test answers

Chaperone-SA-1.0 and other models on 473 held-out test labels. Now on AWS and Azure Marketplace. See the results →

ParaTrace v7 — real API results Strict setting
seminar-essay.txtAI-written

In today's rapidly evolving digital landscape, remote work has fundamentally reshaped how organizations operate, offering employees unprecedented flexibility. However, it is important to note that this shift also presents unique challenges, from maintaining team cohesion to ensuring clear communication. Ultimately, by fostering a culture of trust, organizations can unlock the full potential of a hybrid workforce.

diary-1892.txtHuman · 1892

In the evening we went round to the Cummings’, to have a few fireworks. It began to rain, and I thought it rather dull. One of my squibs would not go off, and Gowing said: “Hit it on your boot, boy; it will go off then.” I gave it a few knocks on the end of my boot, and it went off with one loud explosion, and burnt my fingers rather badly.

study-tips-edited.txtAI-written + attack

Effective time managment is esential for аcademic success. By prioritizing tasks, setting realistc gоals, and minimizing distractions, students can significantly improve thier productivity. Moreover, regular breaks and adequate slеep play a crucial role in maintaining fоcus and overall well-being. Ultimatly, developing these habits early not only enhances academic performance but also lays a strong foundation for lifelong lеarning and personal growth.

AI likelihood >99%
Likely AI-generated High confidence 100% of the text
Likely human-written High confidence 100% of the text
Likely AI-generated High confidence 100% of the text, despite 5 misspellings and 5 look-alike letters
Reading the text…
99.6%
AI text caught
0.84%
human texts flagged
96.0%
caught under attack

Replays of real ParaTrace v7 API results. See the benchmarks →

Models

Chaperone-SA-1.0

Drug-level sentiment for pharma and medical content: labels each drug Positive, Neutral or Negative in one request per document. 91% accurate on 473 held-out test labels; about 31 GB, so it fits on a single L40S. Available on AWS and Azure Marketplace.

View results →
ParaTrace v7

Our own detector for AI-written English. Catches 99.6% of AI answers from 90 models, wrongly flags 0.84% of human texts, and flags no research paper from before ChatGPT.

View benchmarks →
Chaperone-Thinking-LQ-1.0Archived

Open reasoning model: GPTQ + QLoRA on DeepSeek-R1-Distill-Qwen-32B. Medical and scientific corpora. Fully available on Hugging Face.

View results →

Applications

How the language line shows up for teams who never want to touch a checkpoint.

Chatbots

Conversational assistants on your data, privately hosted. Support teams stay on hard tickets; the model handles the rest.

Explore chatbots →
Specificity

Semantic analysis on specialist text — trends, sentiment, and extraction powered by Chaperone-SA, not a generic API.

Explore specificity →

Different corpus, private deploy, or another language task?

Book a technical call