Software comparison

QuickPLS vs SmartPLS

Both applications support PLS-SEM and related methods. QuickPLS also includes guided fsQCA, from calibration to solutions and case inspection.

We tested several datasets and different model types in QuickPLS and SmartPLS. With the same data, model specifications and calculation settings, all the results we compared agreed to three decimal places.

Many of these datasets and models are included as sample projects in QuickPLS. Open a sample project, run its analysis and compare the output in SmartPLS using the same settings. Find a sample project.

Results on the same data and model

All 69 main estimates match to three decimal places.

We compared QuickPLS calculations with SmartPLS results for the same sample dataset, model and analysis settings. All 13 path coefficients, four R² values, 31 indicator loadings and 21 indicator weights agree when rounded to three decimal places.

The example uses 344 responses and a model of reputation, satisfaction and loyalty. The SmartPLS values are from its published teaching tables. Each row below names the result being compared; “Match” means the two displayed values are the same.

Scroll sideways to see all comparison columns.

Structural model: all 13 paths and four R² values
ResultQuickPLSSmartPLSAt three decimals
Path coefficients
Attractiveness → Competence0.0860.086Match
Attractiveness → Likeability0.1670.167Match
Corporate social responsibility → Competence0.0590.059Match
Corporate social responsibility → Likeability0.1780.178Match
Performance → Competence0.2950.295Match
Performance → Likeability0.1170.117Match
Quality → Competence0.4300.430Match
Quality → Likeability0.3800.380Match
Competence → Customer satisfaction0.1460.146Match
Competence → Customer loyalty0.0060.006Match
Likeability → Customer satisfaction0.4360.436Match
Likeability → Customer loyalty0.3440.344Match
Customer satisfaction → Customer loyalty0.5050.505Match
Explained variance (R²)
Competence0.6310.631Match
Likeability0.5580.558Match
Customer satisfaction0.2920.292Match
Customer loyalty0.5620.562Match
Compare all 31 loadings and 21 weights

Scroll sideways to see all comparison columns.

Measurement model: all 52 loadings and weights
ResultQuickPLSSmartPLSAt three decimals
Reflective indicator loadings
Competence / comp_10.8240.824Match
Competence / comp_20.8210.821Match
Competence / comp_30.8440.844Match
Likeability / like_10.8800.880Match
Likeability / like_20.8690.869Match
Likeability / like_30.8440.844Match
Customer satisfaction / cusa1.0001.000Match
Customer loyalty / cusl_10.8330.833Match
Customer loyalty / cusl_20.9170.917Match
Customer loyalty / cusl_30.8430.843Match
Formative indicator loadings
Attractiveness / attr_10.7540.754Match
Attractiveness / attr_20.5060.506Match
Attractiveness / attr_30.8910.891Match
Corporate social responsibility / csor_10.7710.771Match
Corporate social responsibility / csor_20.5710.571Match
Corporate social responsibility / csor_30.8380.838Match
Corporate social responsibility / csor_40.6170.617Match
Corporate social responsibility / csor_50.8480.848Match
Performance / perf_10.8460.846Match
Performance / perf_20.6900.690Match
Performance / perf_30.5730.573Match
Performance / perf_40.7170.717Match
Performance / perf_50.6380.638Match
Quality / qual_10.7410.741Match
Quality / qual_20.5700.570Match
Quality / qual_30.7490.749Match
Quality / qual_40.6640.664Match
Quality / qual_50.7870.787Match
Quality / qual_60.8560.856Match
Quality / qual_70.7220.722Match
Quality / qual_80.6270.627Match
Formative indicator weights
Attractiveness / attr_10.4140.414Match
Attractiveness / attr_20.2010.201Match
Attractiveness / attr_30.6580.658Match
Corporate social responsibility / csor_10.3060.306Match
Corporate social responsibility / csor_20.0370.037Match
Corporate social responsibility / csor_30.4060.406Match
Corporate social responsibility / csor_40.0800.080Match
Corporate social responsibility / csor_50.4160.416Match
Performance / perf_10.4680.468Match
Performance / perf_20.1770.177Match
Performance / perf_30.1940.194Match
Performance / perf_40.3400.340Match
Performance / perf_50.1990.199Match
Quality / qual_10.2020.202Match
Quality / qual_20.0410.041Match
Quality / qual_30.1060.106Match
Quality / qual_4-0.005-0.005Match
Quality / qual_50.1600.160Match
Quality / qual_60.3980.398Match
Quality / qual_70.2290.229Match
Quality / qual_80.1900.190Match

See the data preparation, settings, screenshots and complete comparison ↗ · Download the results

These 69 values are the model’s main estimates. The complete comparison also examines diagnostic results and explains a conflicting value in one later SmartPLS source table.

Feature comparison

Find the methods you use.

Feature names open QuickPLS guides; SmartPLS entries link to official documentation.

Methods, outputs and everyday use
FeatureQuickPLS ProSmartPLS
Model estimation
PLS-SEMIncludedReflective and formative models; paths, loadings and weights.IncludedReflective and formative models; paths, loadings and weights.Source ↗
Consistent PLS (PLSc)IncludedReliability-corrected PLS estimates.IncludedReliability-corrected PLS estimates.Source ↗
Weighted PLSIncludedCase weights in PLS estimation.IncludedCase weights in PLS estimation.Source ↗
CB-SEM and CFAIncludedFactor and structural models, parameter estimates and fit statistics.IncludedFactor and structural models, parameter estimates and fit statistics.Source ↗
GSCAIncludedComponent models, loadings, weights and structural estimates.IncludedComponent models and bootstrapping.Source ↗
Principal component analysisIncludedComponent extraction, scores and rotated outputs.IncludedPrincipal component analysis.Source ↗
Linear and logistic regressionIncludedObserved-variable models for continuous or binary outcomes.IncludedObserved-variable models for continuous or binary outcomes.Source ↗
PROCESS-style analysisIncludedObserved-variable mediation, moderation and conditional effects.IncludedPath analysis, PROCESS and bootstrapping.Source ↗
Follow-up analysis and model checks
BootstrappingIncludedPLS/PLSc resampling; percentile, BCa and studentized intervals in supported workflows.IncludedPercentile, BCa and studentized intervals; consistent bootstrapping for PLSc.Source ↗
Mediation and moderationIncludedDirect, indirect, interaction and conditional effects.IncludedDirect, indirect, interaction and conditional effects.Source ↗
Higher-order constructsIncludedRepeated and extended repeated indicators; embedded and disjoint two-stage approaches.IncludedRepeated and extended repeated indicators; embedded and disjoint two-stage approaches.Source ↗
Reliability and validityIncludedLoadings, reliability, AVE and HTMT/HTMT+.IncludedLoadings, reliability, AVE and HTMT (absolute-correlation HTMT+).Source ↗
PLSpredict and CVPATIncludedHeld-out predictions, error summaries and predictive comparisons.IncludedPLSpredict and CVPAT.Source ↗
MICOM and multigroup analysisIncludedMeasurement invariance and group comparisons for PLS/PLSc.IncludedMICOM and multigroup analysis for PLS/PLSc.Source ↗
Importance–performance analysisIncludedTotal effects and performance for a selected target.IncludedImportance–performance map analysis (IPMA).Source ↗
FIMIX-PLS and PLS-POSIncludedMixture and prediction-oriented segmentation workflows.IncludedFIMIX-PLS and PLS-POS.Source ↗
NCAIncludedCeiling lines, effect sizes, bottlenecks and permutation tests.IncludedCeiling lines, effect sizes, bottlenecks and permutation tests.Source ↗
Set analysis
fsQCAIncludedGuided study, calibration, truth tables, solutions and case inspection.Not documentedNo fsQCA analysis workflow is described in the current method catalogue; see the source note.Source ↗
Multi-value QCA and Coincidence AnalysisIncludedDedicated workflows for categorical conditions and causal configurations.Not documentedThese workflows are not listed in the current method catalogue.Source ↗
fsQCA outcome and robustness comparisonsIncludedCompare outcome presence/absence and inspect changes across calibration choices.Not documentedThese fsQCA workflows are not listed in the current method catalogue.Source ↗
Everyday use
Visual model editingIncludedDraw constructs and paths on a model canvas.IncludedDraw constructs and paths on a model canvas.Source ↗
Saved projects and reportsIncludedSave the model and calculated results; prepare a report and export tables as CSV.IncludedSave projects; export HTML/Excel reports and copy tables.Source ↗
Sample projectsIncludedBundled examples plus downloadable practice studies.IncludedBundled and downloadable sample projects.Source ↗
Learning resourcesIncludedMethod guides and paper tutorials with practice data and worked answers.IncludedMethod documentation, case studies, books and courses.Source ↗
Desktop platformsWindowsWindows x64. macOS edition coming soon.Windows, macOS, LinuxWindows, macOS and Linux.Source ↗
Sources and comparison notes

Sources checked on 8 November 2026: QuickPLS guides and SmartPLS documentation. The table compares available tasks; individual settings and output definitions can differ.

QuickPLS includes a guided fsQCA workflow. SmartPLS’s current method catalogue does not document an fsQCA analysis workflow, although an older capability page mentions fsQCA. This is why the table says “Not documented” for that entry.

QuickPLS Pro is free to download and use. See QuickPLS access details and the SmartPLS website for product information.

Try a model you already know.

  1. Start with the data. Export a copy of your dataset and note how missing values were treated.
  2. Recreate the model. Use the same indicators, construct types and structural paths in QuickPLS.
  3. Match the settings. Check weighting, standardisation and the analysis options before running it.
  4. Compare the output. Compare the same named tables at the same precision, then save your QuickPLS project.

SmartPLS project files are not imported directly; this walkthrough starts from your data and model specification.

Also compare QuickPLS vs lavaan and QuickPLS vs cSEM.

SmartPLS is a trademark of SmartPLS GmbH. QuickPLS Pro is independently developed and is not affiliated with or endorsed by SmartPLS GmbH.