> For the complete documentation index, see [llms.txt](https://docs.rumi.systems/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.rumi.systems/performance/canonical-benchmark/test-results.md).

# Test Results

This section contains performance benchmark results for Rumi releases. Results are organized by major release version, with detailed results provided for each specific release tested.

## Organization

Performance results are structured as follows:

* **Release Line** (e.g., Rumi 4.0) - Groups results for a major release line
  * **Specific Release** (e.g., Rumi 4.0.579-4.0.39) - Contains actual test results for that release (Core version - Bindings version)

## Available Results

### Rumi 4.0

* [Rumi 4.0.579-4.0.39](/performance/canonical-benchmark/test-results/4.0/4.0.579-4.0.39.md) - Core: 4.0.579, Bindings: 4.0.39 (February 2025)

## Understanding the Results

Each release results page includes:

### Latency Results

* 50th, 99th, and 99.9th percentile latencies in microseconds
* Results for both Indirect and Direct message access methods
* Results across MinCPU, Default, and MaxCPU configurations
* Latency-optimized configuration results

### Throughput Results

* Maximum messages per second under saturated load
* Results for both Indirect and Direct message access methods
* Results across MinCPU, Default, and MaxCPU configurations
* Throughput-optimized configuration results

### Performance Analysis

* Key performance characteristics
* Optimal configurations for different use cases
* Tuning recommendations
* Comparisons with previous releases (where applicable)

## Test Methodology

All results are generated using the same canonical benchmark described in the [Test Description](/performance/canonical-benchmark/test-description.md). This ensures:

* **Consistency** - Direct comparability across releases
* **Reproducibility** - Same hardware, configuration, and methodology
* **Transparency** - Full disclosure of test parameters

## Next Steps

* View [Test Description](/performance/canonical-benchmark/test-description.md) for complete test methodology
* Select a release above to view detailed results
* Return to [Canonical Benchmark Overview](/performance/canonical-benchmark.md)
* Explore [Performance Benchmark Suite](/performance/benchmark-suite.md) for the full benchmark suite