Productivity
Papers AI
Last updated 2026-08-25 · benchmark measured 2026-11-07 — deterministic & reproducible
Papers AI is a research workspace combining writing, data, references, and code in one place.
Papers AI at a glance
Papers AI is a research workspace from Overleaf that combines writing (Word, Markdown, LaTeX, Typst), Jupyter notebooks, reference management, and an AI assistant in one place for researchers, PhD students, research scientists, academic writers, and data analysts.
Good for
- Writing a paper while running code and analysis in the same project instead of switching tools
- Getting AI help that already knows the whole project's documents and data without re-uploading files
- Collaborating with coauthors in real time or working offline with files kept on your device
Pricing
Free plan (£0) with generous AI allowance; Plus plan £10/month, billed monthly, cancel anytime, with 5x more AI usage.
Questions people ask
Where does my data live?
Your files stay on your device by default, and nothing syncs to Papers AI's servers unless you turn on collaboration for that project.
Can I use Papers AI for unpublished or sensitive research data?
Yes, Papers AI runs locally, but you should check your institution's data policy for projects involving identifiable human subject data.
Is my data used to train Papers AI's models?
No, according to Papers AI your projects are never used for model training.
Can I use my own AI model instead of the built-in one?
Yes, you can connect an OpenRouter key or a local model via Ollama, LM Studio, vLLM, or any OpenAI-compatible endpoint.
How is Papers AI different from Papers by ReadCube?
Papers by ReadCube is now just ReadCube; Papers AI is a separate workspace covering writing, code, and research needs in whatever format you prefer.
Written by Legit.Show from papers.ai on 2026-10-25. It does not change the score.
Are you the maker of Papers AI? Claim this listing. It is free, takes a meta tag, a DNS record or GitHub admin rights, and never changes the score.
Launched something? Add your product, free.
To cite this score: legit.show/s/papers-ai/2026-11-07. That address never changes; this page moves with every re-measure.
Legit.Show scored Papers AI 92/100 on 2026-11-07, measured across all 7 frames from its public surface. legit.show/s/papers-ai/2026-11-07
Is Papers AI production-ready?
Legit.Show scores Papers AI 92 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Papers AI (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Security; its weakest is Reliability. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 76/100
- Accessibility — 96/100
- Security — 100/100How this compares across the catalogue: The Web Security Baseline
- Privacy — 100/100How this compares across the catalogue: The Privacy Gap
- Reliability — 75/100
- Standards — 100/100
- Discoverability — 100/100
What we measured
- Security headers present: CSP, HSTS, X-Frame-Options, X-Content-Type-Options, Referrer-Policy.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 914 ms to first byte.
- 3 of 3 sampled routes reachable.
- Has a reachable privacy policy.
- Sets cookies / loads scripts with no consent prompt.
- Discoverable: structured data, sitemap, OpenGraph image, canonical URL.
Who it's for
Researchers · PhD students · Research scientists · Academic writers · Data analysts
Pricing
Free plan available; Plus plan £10/month (billed monthly, cancel anytime)
Sources and updates
- Description
- Taken from papers.ai's own website on 2026-08-25.
- Operator
- Digital Science UK Limited, as named in papers.ai's terms, privacy page or footer.
- Benchmark
- Measured by Legit.Show from the live site, the way any visitor sees it — with no access to its code or accounts. Same method for every product, and no AI decides the score. Last checked 2026-11-07.
Put together from public information, without Papers AI's involvement. If anything here is wrong, tell us and a person will check it.
Visit Papers AI → · Alternatives to Papers AI → · How this was measured →