Debug & Review · LOCAL TOOL
Duration Distribution Bench
Paste non-negative duration samples in milliseconds to calculate minimum, maximum, mean, p50, p90, p95, and p99, with a simple threshold-relative distribution.
No API call
Your input
LOCALResult
Run the tool to see a result.
Your result will appear here. Input is not saved.
WHY THIS TOOL EXISTS
A focused job, not a black box.
The quantile method and sample count are visible, and strict threshold exceedances are counted separately. This supports reproducible discussion of a timing excerpt without claiming a live performance measurement.
How to use it
- Collect comparable timings and paste their millisecond values.
- Enter the threshold relevant to this sample.
- Review the nearest-rank percentiles, mean, and number strictly above the threshold.
TRY A WORKING EXAMPLE
Start with known input.
Load this sample into the workspace, run the tool, and compare the result shown below.
Show sample input
{
"source": "20, 25, 30, 35, 40, 50, 70, 90, 120, 300",
"threshold": "100"
}Expected sample result from the local tool
10 sample(s) · 2 above threshold.
{
"unit": "milliseconds",
"count": 10,
"minimum": 20,
"maximum": 300,
"mean": 78,
"p50": 40,
"p90": 120,
"p95": 300,
"p99": 300,
"method": "nearest rank",
"threshold": 100,
"exceeded": 2,
"bins": [
{
"label": "0–25% of threshold",
"count": 2
},
{
"label": ">25–50%",
"count": 4
},
{
"label": ">50–100%",
"count": 2
},
{
"label": "above threshold",
"count": 2
}
]
}LIMITS AND INTERPRETATION
What the result cannot tell you.
Up to 10000 samples. Nearest-rank percentiles can be coarse for small samples. The tool does not collect timings, establish statistical significance, or make a service-level guarantee.
Inputs are processed in this page and are not written to local storage.