Enum BenchmarkMetric

Namespace

AiDotNet.Enums

Assembly

AiDotNet.dll

Defines standardized metrics used in benchmark reports.

public enum BenchmarkMetric

Fields

Accuracy = 0

Proportion of correct answers (0.0 to 1.0).

AverageConfidence = 1

Average confidence value (0.0 to 1.0) when available.

AverageTimePerItemMilliseconds = 5

Average time per item in milliseconds.

CorrectCount = 3

Number of correct items.

MeanSquaredError = 6

Mean squared error (regression-style error metric).

RootMeanSquaredError = 7

Root mean squared error (regression-style error metric).

TotalDurationMilliseconds = 4

Total duration in milliseconds.

TotalEvaluated = 2

Total number of items evaluated.

Remarks

For Beginners: Benchmarks produce scores and measurements. This enum provides a type-safe, standardized vocabulary for common metrics so we avoid "stringly-typed" metric keys.