Regression explorer

SLM Regression Line Benchmark

Choose a benchmark, fit a linear regression on log10(parameters), and compare models to the size trend. Search and org filters only change what is visible. The regression line stays anchored to the full eligible dataset for the selected benchmark. Models below 500k parameters are clipped from the plot and excluded from the fit so they do not crush the scale.

Average score vs log parameters

Silver regression line fit globally for the selected benchmark. Search and org filtering only hide points.

Hover for details. Click a point to open the model page. The line is fit globally for the selected benchmark.
0 visible / 0 fit
Selected benchmark
Avg
Visible models
0
Fit models
0
Mean absolute residual
—
Residual spread
—
Visible match rate
—
Visible orgs
—
Plot mode
Silver
Disclaimer: the regression line is fit only to the full eligible dataset for the selected benchmark, using log10(parameters) as x and the selected benchmark score as y. Search and org filtering only hide points from the chart. Residuals are measured in score points after converting scores to percentages. RMSE is the square root of mean squared error, and R² describes how much of the variation is explained by the line. Models with fewer than 500k parameters are clipped from the view and excluded from the fit so they do not compress the plot.
Contribute
Want to add your model? Open a discussion or PR.
Send a model link, and it can be reviewed for inclusion.
Deep dive
Need a more detailed breakdown of your model?
Go here for a fuller analysis and broader comparisons.