Softwr
JMP logo

JMP

Desktop statistical and design of experiments software from a SAS subsidiary

As of 13 November 2026, JMP is free to use. JMP is an interactive statistics package for Windows and macOS, strongest at design of experiments and used heavily in semiconductor, chemical and pharmaceutical process work. Softwr lists it under Machine Learning. JMP is made by SAS Institute, launched in 1976, available on macOS, Windows.

Overview

What is JMP?

JMP is desktop statistical software sold by JMP Statistical Discovery, a subsidiary of SAS Institute. It runs on Windows and macOS as an application, not a service. Everything about it is interactive: a data table, analysis platforms opened from menus, and graphs linked so that selecting points in one view highlights the same rows everywhere else. It is scripted in JSL, its own language, which records what you did through the interface and can be saved as an add-in. JMP Pro is a separately licensed and more expensive edition that adds predictive modelling, cross validation, generalised regression, model comparison and text analysis. Licences are per named user on an annual subscription. The thing that distinguishes it from every other tool in this category is design of experiments. Its custom designer takes a set of factors, constraints, a model you want to be able to estimate and a run budget, and produces an experimental design that gets you there in the fewest physical runs. That is not machine learning in the modern sense, it is deciding which experiments to perform before any data exists, and when each run is a wafer lot or a pilot batch the savings are measured in weeks of plant time. This is why JMP is standard in fabs and process development groups, and it is bought by engineers and scientists rather than by data platform teams. The trade-off is that it stops at the desktop. The working data set must fit in the workstation's memory, there is no Linux build, and there is nothing to schedule; a recurring analysis is run by a person opening a file. Models leave as exported scoring code in SQL, C, Python or SAS, which somebody else then owns in a different system, and there is no registry, monitoring or retraining. The analysis knowledge a team builds accumulates in JSL scripts and JMP journals that only JMP opens, which is a quiet form of lock-in that only becomes visible when a licence renewal is questioned.

What people use it for

  • Planning a physical experiment where each run is expensive, and the question is which twelve runs to perform rather than how to model data you already have
  • Process capability and control chart work in a manufacturing quality function that has to produce evidence for a customer or regulator
  • Exploratory analysis by an engineer or scientist who will not write code but needs more than a spreadsheet
  • Semiconductor, chemical and pharmaceutical development groups where JMP is already the shared language for reporting results

The honest half

Where does JMP fall short?

Each is concrete and checkable: the half of a review a vendor will not write.

  • It is a desktop application holding the working table in memory, so a data set that outgrows the workstation has no in-place upgrade path, only a move to a different tool and a different skill set.
  • There is no Linux build and no server edition for running analyses, so JMP cannot sit in a scheduled pipeline the way an R or Python script can, and recurring reports depend on a named person running them on a laptop.
  • The predictive modelling capability most buyers mean when they call this machine learning software is in JMP Pro, a separate and more expensive licence, so the base product's price is not the price of the thing being evaluated.
  • JSL is proprietary to JMP, so the scripts, add-ins and automation a group accumulates over a decade do not port anywhere and become sunk cost the moment anyone questions the renewal.
  • Deployment ends at exported scoring code with no registry, monitoring or retraining, so a model that runs in production is maintained by another team in another language and steadily diverges from the version the analyst still has open.

Cross-shopped

What are the alternatives to JMP?

The closest alternatives to JMP are Azure Machine Learning and DataRobot. Each is a tool buyers genuinely weigh against it, with the reason why.

Pricing

How much does JMP cost?

JMP has a free plan, and paid plans start at $1785/yr, across 2 plans. Taken from the vendor's own pricing page; prices move, so check before you buy.

Trial

Free

  • 30-day trial
  • Full features

JMP

$1,785 /yr

  • Core JMP
  • Standard features

Capabilities

What can JMP do?

JMP lists 8 features, including custom design of experiments, linked interactive graphics and analysis platforms.

  • Custom design of experiments

    Generates optimal designs for stated factors, constraints and run budgets, including definitive screening designs

  • Linked interactive graphics

    Selecting rows in one plot highlights them in every other open view of the same table

  • Analysis platforms

    Menu-driven fitting for regression, ANOVA, multivariate methods, reliability and survival

  • Quality and process tools

    Control charts, process capability, measurement systems analysis and gage studies

  • Graph Builder

    Drag-and-drop construction of layered plots without writing plotting code

  • JSL scripting

    Records interface actions as reusable scripts and supports add-in development

  • Scoring code export

    Emits fitted model formulas as SQL, C, Python, JavaScript or SAS for use outside JMP

  • Predictive modelling in JMP Pro

    Adds validation, penalised regression, boosted trees, neural networks and model comparison

Answered, with sources

Questions people ask

Each answer names the page it came from, so you can check it rather than take our word for it.

Is JMP the same thing as SAS?

No. JMP is a separate desktop product from a SAS subsidiary, with its own interface, its own scripting language and its own licence. Knowing SAS does not transfer to it beyond the statistics.

Do I need JMP Pro?

If you want cross validation, penalised regression, boosted trees or neural networks, yes. The base edition covers classical statistics, graphics and design of experiments well and stops short of predictive modelling.

Does it run on Linux?

No. Windows and macOS only, as an installed application.

Can I put a JMP model into production?

Only by exporting the scoring formula as SQL, C, Python or similar and running it in another system. JMP itself does not serve, monitor or retrain models.

Who actually uses it?

Process and quality engineers, and scientists in R&D, particularly in semiconductor, chemicals, pharmaceutical and medical device work. It is not usually chosen by data engineering or platform teams.

Behind it

Who makes JMP?

JMP is made by SAS Institute, founded in 1976 and based in Cary, North Carolina.

Company
SAS Institute
Based in
Cary, North Carolina
Share

Keep looking

Where to go from JMP

Best Machine Learning software for

Compare JMP with

Other Machine Learning software

  • Programming and numeric computing platform

    From $940/yr12 researched notes
  • Enterprise AI platform for automated machine learning

    12 researched notes
  • Microsoft's managed platform for training, tracking and deploying models on Azure

    Free plan13 researched notes
  • Statistical analysis software for data science

    Free, then $99/mo7 researched notes
  • Statistical software for quality engineering, and the tool Six Sigma training is written around

    From $2,394/yr11 researched notes
  • Data science software for research professionals

    From $48/yr10 researched notes
  • Interactive computing across all programming languages

    Free plan9 researched notes
  • Developer tools for machine learning

    Free, then $60/mo10 researched notes
  • Data mining and visualization toolkit

    Free plan8 researched notes
  • Unified analytics platform for data engineering and data science

    Free plan15 researched notes
  • The AI Data Cloud for enterprise data warehousing

    Free plan12 researched notes
  • Open source data analytics and integration platform

    Free, then $19/mo11 researched notes
  • Build applications with LLMs through composability

    Free plan10 researched notes
  • Vector database for machine learning

    Free, then $20/mo10 researched notes
  • Deep learning framework with dynamic computation graphs

    Free plan9 researched notes
  • Machine learning in Python

    Free plan16 researched notes

Softwr does not host reviews and shows no star rating for JMP, because a rating we did not collect is not ours to publish. What is here is the pricing and platform detail from the vendor’s own pages, limitations we could state concretely, and alternatives a reviewer confirmed people weigh against it. Tell us if any of it is wrong.

More on JMP

Best Machine Learning software alternatives

Open-source MLOps platform for experiment tracking and orchestration

Open-source self-hosted, with paid hosted and enterprise tiers

Model-agnostic SDK for AI orchestration

Open source, no pricing

LLM engineering platform for testing and evaluating AI agents in production

Tiered subscription with usage-based overage charges

Open-source AI orchestration framework for LLM applications

Open-source with optional paid enterprise support

Generative media inference platform for developers

usage-based

Platform for tracking, comparing, and optimizing ML experiments

freemium

Open source Python framework that packages models into deployable inference services

freemium

Compare JMP with alternatives