Skip to content

results.md

Latest commit

 

History

History
84 lines (59 loc) · 4.4 KB

results.md

File metadata and controls

84 lines (59 loc) · 4.4 KB
Raw

Benchmark results

These are measured results produced by the Neuron-JS benchmark harness (yarn benchmark). They compare @sebasoft/neuron-js against json-rules-engine, json-logic-js, a hand-coded TypeScript baseline, and rule-engine-js across the pricing, eligibility, and workflow-routing scenarios. See the methodology for how each metric is collected.

Numbers reflect a single machine, Node version, and commit; reproduce locally before citing. No value on this page is hand-entered — charts and the table below are generated from the same source file.

Provenance

Field Value
Generated 2026-06-23T13:23:56.971Z
Node v24.14.1
Commit 2f5894a2c23f0ecd5656e1625299510fe670a622
Neuron-JS version 0.5.2
Command yarn benchmark
Raw source benchmarks/results/latest.actual.json

Throughput comparison

metric: throughput_decisions_per_second · decisions / second · higher is better

Throughput comparison by engine, measured Neuron-JS benchmark output.

Cold-start comparison

metric: cold_start_ms · milliseconds · lower is better

Cold-start comparison by engine, measured Neuron-JS benchmark output.

Bundle-size comparison

metric: bundle_size_minified_bytes · minified bytes (esbuild, node platform) · lower is better

Bundle-size comparison by engine, measured Neuron-JS benchmark output.

Validation overhead

metric: validation_overhead_ms · milliseconds per decision · lower is better

Validation overhead by engine, measured Neuron-JS benchmark output.

Neuron-JS differentiator: competitors provide no schema-validation step (0).

Explanation overhead

metric: explanation_overhead_ms · milliseconds per decision · lower is better

Explanation overhead by engine, measured Neuron-JS benchmark output.

Neuron-JS differentiator: competitors provide no explanation trace (0).

Full results (medium · 10,000 decisions)

Throughput is decisions/second (higher is better); all latency, cold-start, and overhead columns are milliseconds (lower is better); bundle size is minified bytes.

Engine Scenario Throughput p50 ms p95 ms Cold start ms Bundle B Validation ms Explanation ms
@sebasoft/neuron-js pricing-discount 1,262,699 0.000757 0.000961 7.54 13,040 0.000243 0
@sebasoft/neuron-js eligibility-approval 1,362,127 0.000692 0.000859 7.54 13,040 0.000425 0.000058
@sebasoft/neuron-js workflow-routing 1,221,362 0.000784 0.000959 7.54 13,040 0.000472 0.000042
json-rules-engine pricing-discount 199,100 0.004799 0.006327 9.167 81,550 0 0
json-rules-engine eligibility-approval 217,491 0.004434 0.005789 9.167 81,550 0 0
json-rules-engine workflow-routing 217,969 0.004448 0.005439 9.167 81,550 0 0
json-logic-js pricing-discount 3,764,115 0.000243 0.000376 1.652 5,544 0 0
json-logic-js eligibility-approval 4,875,373 0.000188 0.000203 1.652 5,544 0 0
json-logic-js workflow-routing 5,047,319 0.000187 0.000197 1.652 5,544 0 0
hand-coded-typescript pricing-discount 11,695,332 0.000088 0.000092 0.981 0 0 0
hand-coded-typescript eligibility-approval 10,362,694 0.000082 0.000118 0.981 0 0 0
hand-coded-typescript workflow-routing 12,090,685 0.00008 0.000083 0.981 0 0 0
rule-engine-js pricing-discount 844,734 0.00109 0.001835 2.725 46,165 0 0
rule-engine-js eligibility-approval 902,843 0.001062 0.001385 2.725 46,165 0 0
rule-engine-js workflow-routing 852,630 0.001126 0.001448 2.725 46,165 0 0

Validation and explanation overhead are Neuron-JS capabilities (validateScript, explainExecution); the other engines provide no equivalent step, so their measured delta is 0.