Struct BenchmarkResults

Source

pub struct BenchmarkResults {
    pub benchmark_name: String,
    pub total_problems: usize,
    pub correct: usize,
    pub accuracy: f32,
    pub avg_confidence: f32,
    pub avg_latency_ms: f64,
    pub total_tokens: usize,
    pub category_accuracy: HashMap<String, f32>,
    pub difficulty_accuracy: HashMap<u8, f32>,
    pub results: Vec<EvaluationResult>,
    pub calibration: CalibrationMetrics,
}

Expand description

Aggregate benchmark results

Fields§

§benchmark_name: String§total_problems: usize§correct: usize§accuracy: f32§avg_confidence: f32§avg_latency_ms: f64§total_tokens: usize§category_accuracy: HashMap<String, f32>

Accuracy by category

§difficulty_accuracy: HashMap<u8, f32>

Accuracy by difficulty

§results: Vec<EvaluationResult>

Individual results

§calibration: CalibrationMetrics

Calibration metrics

Implementations§

Source §

impl BenchmarkResults

Source

pub fn compute(benchmark_name: &str, results: Vec<EvaluationResult>) -> Self

Source

pub fn compare(&self, baseline: &BenchmarkResults) -> ComparisonReport

Generate a comparison report against baseline

Trait Implementations§

Source §

impl Clone for BenchmarkResults

Source §

fn clone(&self) -> BenchmarkResults

Returns a duplicate of the value. Read more

1.0.0 · Source§

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source. Read more

Source §

impl Debug for BenchmarkResults

Source §

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter. Read more

Source §

impl<'de> Deserialize<'de> for BenchmarkResults

Source §

fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer. Read more

Source §

impl Serialize for BenchmarkResults

Source §

fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
where S: Serializer,

Serialize this value into the given Serde serializer. Read more

Auto Trait Implementations§

§

impl UnwindSafe for BenchmarkResults

Blanket Implementations§

Source §

impl<T> Any for T
where T: 'static + ?Sized,

Source §

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more

Source §

impl<T> Borrow<T> for T
where T: ?Sized,

Source §

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more

Source §

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source §

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more

Source §

impl<T> CloneToUninit for T
where T: Clone,

Source §

unsafe fn clone_to_uninit(&self, dest: *mut u8)

🔬This is a nightly-only experimental API. (clone_to_uninit)

Performs copy-assignment from self to dest. Read more

Source §

impl<T> From<T> for T

Source §

fn from(t: T) -> T

Returns the argument unchanged.

Source §

impl<T> FromRef<T> for T
where T: Clone,

Source §

fn from_ref(input: &T) -> T

Converts to this type from a reference to the input type.

Source §

impl<T> Instrument for T

Source §

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided Span, returning an Instrumented wrapper. Read more

Source §

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more

Source §

impl<T, U> Into for T
where U: From<T>,

Source §

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Source §

impl<T> IntoEither for T

Source §

fn into_either(self, into_left: bool) -> Either<Self, Self>

Converts self into a Left variant of Either<Self, Self> if into_left is true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more

Source §

fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
where F: FnOnce(&Self) -> bool,

Converts self into a Left variant of Either<Self, Self> if into_left(&self) returns true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more

Source §