Latest Benchmark

Rolling nightly benchmark compiled from the live operational runs. Snapshot label: latest-2026-08-27T2005Z.

Trained params is the average non-zero parameter count in the fitted model across folds. Avg active params / classification is the mean number of active parameters or scoring decisions touched while classifying one product.

3,639Filtered products

1,436Filtered tags

255Filtered taxonomies

79Prime base

View UMLLR tag-order ablation View operational UMLLR page

Benchmark dashboard chart for latest benchmark view — Small-multiples dashboard generated directly from the comparison table rows below.

Model comparison chart for latest benchmark view — Log-log scatter of trained parameters versus mean p-adic loss, overlaid with the current parsimoniousness baseline.

Active parameter comparison chart for latest benchmark view — Scatter plot of avg active params versus mean p-adic loss, excluding PCLR and PCNN. Fitted equation: mean p-adic loss = -0.1099 log10(active params) + 0.4286. Regression fitted on log10(active params): R²=0.384, p=0.138.

Active parameter versus log-loss chart for latest benchmark view — Scatter plot of avg active params versus log10(mean p-adic loss), excluding PCLR and PCNN. Fitted equation: log10(mean p-adic loss) = -0.1623 log10(active params) - 0.4521. Regression fitted on log10(active params): R²=0.613, p=0.037.

Model	Trained params	Mean p-adic loss	Exact acc.	Prefix-2 acc.	Avg active params / classification
Dummy Baseline	1.0	0.846391	7.61%	0.00%	1.00
Importance-Optimised p-adic Linear Regression	268.6	0.237259	68.15%	60.65%	0.84
Parameter-constrained Logistic Regression	8329.2	0.766468	14.37%	18.53%	409.81
Unconstrained Logistic Regression with L1	1848.0	0.118603	75.74%	71.98%	260.77
Parameter-constrained Neural Network	7958.2	0.670245	21.45%	17.63%	7111.04
Decision Tree	12411.5	0.134472	72.34%	70.77%	154.27
Level-wise Logistic Regression	70882.0	0.139314	70.43%	69.40%	221.96
Unconstrained Neural Network with L2	20525.2	0.120907	75.60%	72.02%	3353.04
Zubarev (greedy init.)	301.2	0.261013	64.88%	58.17%	0.98