note.md vs Surge AI

Side-by-side comparison of features, pricing, and ratings

Analysis reviewed Live tool data as of 2026-10-09
Cross-checked through our multi-step verification ·
Saved

At a glance

Dimensionnote.mdSurge AI
PricingFreemium (Free tier; Premium subscription)Contact sales (custom pricing)
Target UserPhD students, academic researchers, scholarsFrontier AI labs, AI safety teams, enterprise AI builders
Primary FunctionLocal-first reading, note-taking, citation management for research papersExpert human feedback for RLHF, red teaming, benchmarking
Key FeatureReading Studio, smart citations, graph view, local AI semantic searchCurated domain experts; proprietary benchmarks (Antidote, Riemann-bench)
PlatformMac desktop app (local-first)Cloud-based via API/SDK
Best ForIndividual researchers needing a unified workspace for papers and writingComplex, reasoning-intensive AI evaluation tasks
note.md
note.md

Local-first academic IDE for Mac: read papers, cite sources, and write your thesis in one private app

Visit Website
Surge AI
Surge AI

Surge AI supplies expert human RLHF data, red teaming, and public benchmarks like GDP.pdf and the Tuesday Work Index for frontier model

Visit Website
Pricing
Freemium
Contact Sales
Plans
$0
$8.99/mo
$49.99/yr
$99.99 once
$4.99/mo
$29.99/yr
—
Popularity
7 views
7.4k views
Skill Level
Intermediate
Advanced
API Available
Platforms
Desktop
Web
Categories
🔬 Research & Education📝 Notes & Knowledge Management🎓 Academic Writing & Citations
🏷️ Data Labeling & Training Data
Features
Local-first markdown editor and private vault on macOS
Reading Studio: side-by-side PDF reading and highlighting in one pane
Smart citations generated as BibTeX or APA from PDF metadata
/cite anchors citations to a bookmark with one-click return to the passage
Block-based markdown with slash commands (/cite, /pdf, /link, /wiki)
Source and literature management with one-click .bib export
Graph View of articles and sources with Neo4j-friendly export
Bidirectional links that build the knowledge graph as you write
GitHub-flavored markdown, complex tables, and LaTeX math
Semantic search by meaning over indexed passages (Premium, local AI)
Automatic indexing of figures, charts, and tables from PDFs (Premium)
Matrix extraction fills literature-review tables with editable AI suggestions (Premium)
Evidence Scan finds supporting, contradicting, and nuanced passages (Premium)
On-device AI: no cloud upload, no model training on your notes
Works offline and stores data as plain markdown and PDF files
Expert human workforce of doctors, lawyers, engineers, and writers for frontier AI data
RLHF preference data collection and human feedback for model fine-tuning and post-training
Red teaming and adversarial testing staffed with credentialed domain specialists
Off-the-shelf post-training runs built on expert evaluation data
SWE consultant network for software engineering and technical tasks
Agentic coding task sets: 1,700 tasks gave Kimi K2.7 +20.0pp on SWE-Marathon and +12.4pp on DeepSWE
GDP.xlsx benchmark for professional spreadsheet comprehension, spanning 70 tasks across 12 knowledge-work domains
sudo L7 benchmark for staff-level engineering judgment in coding agents
GDP.pdf benchmark for real-world professional document comprehension, cited in the GPT-5.6 release
Chartography benchmark for chart reasoning: Kaplan-Meier curves, candlesticks, contour maps, Bode plots
ComplexConstraints benchmark for instruction following with mutually dependent constraints
HANDBOOK.md benchmark for long-context policy adherence against expert handbooks
DAYJOB vertical benchmark suites for economically valuable agents in Healthcare and Finance
Tuesday Work Index composite benchmark scoring frontier models on real professional work
RL environments including CoreCraft and EnterpriseBench with Python SDK and REST API access

What real users say: note.md vs Surge AI

Not marketing copy and not our opinion — a structured sweep of public discussion (reviews, forums, communities and video comments), showing what people praise and what they complain about for each tool.

note.md

13 mentions across 3 sources · 43% positive — mixed (averaged across 3 sources)

Hacker News, Product Hunt, Bluesky

What users praise

  • • Local-first markdown ensures no vendor lock-in and full privacy.
  • • Unifies PDF reading, note-taking, citations, and writing in one app.
  • • Local AI runs on-device, no data sent to cloud—great for sensitive research.
  • • Smart citations generate BibTeX/APA from PDF metadata automatically.

What frustrates them

  • • Mac-only—no Windows or Linux support confirmed.
  • • No cross-device sync; all files stored locally on one machine.
  • • Limited community feedback; early stage, few user reviews.
  • • Premium AI pricing not disclosed; potential cost concern.

Researched Jul 4, 2026

Surge AI

48 mentions across 3 sources · 38% positive — critical (weighted across 3 sources)

Hacker News, YouTube, Lemmy

What users praise

  • • Credentialed workforce of doctors, lawyers and engineers instead of generic crowd annotators
  • • GDP.pdf cited by OpenAI in the GPT-5.6 release with a concrete 30.7% flagship score
  • • Kimi K2.7 post-training run published measurable SWE-Marathon, DeepSWE and Terminal-Bench gains
  • • Benchmark catalog spans chart reasoning, dependent constraints, long-context policy and verticals

What frustrates them

  • • Contact-only pricing means no public rate card, no tiers, and no way to self-serve
  • • Benchmark sponsorship and independence questions raised directly in HN threads
  • • Expert-credential verification process is never explained in any community source
  • • No community data on support responsiveness, uptime, or SLAs at enterprise scale

Researched Oct 7, 2026

Who should pick which

  • AI safety team at a frontier lab
    Pick: Surge AI

    Needs expert red teaming and RLHF feedback; Surge provides domain experts and benchmarks like Antidote and Riemann-bench for rigorous evaluation.

  • PhD student in computational biology
    Pick: note.md

    Manages many PDF papers, needs citation management, markdown notes, and local AI search—all in one Mac app, private and offline.

  • Enterprise building a document-understanding AI
    Pick: Surge AI

    Requires expert-labeled data for complex PDF tasks; Surge's GDP.pdf benchmark and expert workforce are ideal.

  • Graduate student writing a thesis
    Pick: note.md

    Needs unified reading, note-taking, and citation workflow; note.md's Reading Studio and smart citations streamline the process.

  • Research group evaluating LLM creative writing
    Pick: Surge AI

    Requires expert human evaluation; Surge's Hemingway-bench and Antidote leaderboard provide structured creative writing assessment.

Frequently Asked Questions

Can I use Surge AI for simple sentiment analysis?

No, Surge is designed for complex, reasoning-intensive tasks; for simple classification, other tools are more appropriate.

Is note.md available on Windows or Linux?

No, note.md is a Mac-only desktop app. No Windows or Linux support.

Does Surge AI offer a self-serve platform?

No, Surge requires contacting sales and is customized for enterprise needs.

Can I export notes from note.md?

Yes, notes are stored as plain markdown files with LaTeX, ensuring no lock-in.

What benchmarks does Surge AI provide?

Surge offers Antidote, Riemann-bench, GDP.pdf, ComplexConstraints, Hemingway-bench, EnterpriseBench, and more.

Does note.md have real-time collaboration?

No, note.md is designed for individual users and does not support real-time collaboration.

Which tool is better for a solo AI researcher building a model?

If you need expert human feedback for RLHF, Surge AI is suited; if you are writing a paper on your research, note.md helps manage literature.

What recent news is there about Surge AI?

Microsoft used Surge to evaluate its MAI-Thinking-1 model; Surge also released new benchmarks like Riemann-bench and ComplexConstraints.

More note.md or Surge AI comparisons

Explore each tool further

Browse these categories

Still deciding? Get the weekly AI tools brief

One email a week — new tools, honest comparisons, no spam.

Last reviewed: July 2, 2026