Struct EvalReport 

pub struct EvalReport {
    pub mean_score: f64,
    pub p50_latency_ms: u64,
    pub p95_latency_ms: u64,
    pub total_tokens: u64,
    pub cases_scored: usize,
    pub cases_total: usize,
    pub is_partial: bool,
    pub error_count: usize,
    pub per_case: Vec<CaseScore>,
}

Aggregate evaluation report returned by Evaluator::evaluate.

mean_score is NaN when no cases were successfully scored — callers must check cases_scored > 0 or mean_score.is_finite() before using it as an acceptance threshold.

Examples

use zeph_experiments::EvalReport;

// mean_score is NaN when no cases are scored
// This is a documentation-only example; construct via Evaluator::evaluate in practice.
let partial_report_has_nan_mean = f64::NAN;
assert!(partial_report_has_nan_mean.is_nan());

Fields

mean_score: f64

Mean score across all successfully scored cases (NaN if cases_scored == 0).

p50_latency_ms: u64

Median (p50) latency in milliseconds across scored cases (0 if none).

p95_latency_ms: u64

95th-percentile latency in milliseconds across scored cases (0 if none).

total_tokens: u64

Total tokens consumed by all judge calls in this evaluation.

cases_scored: usize

Number of cases that were successfully scored.

cases_total: usize

Total number of cases in the benchmark set (including failed ones).

is_partial: bool

true if any case was excluded due to budget exhaustion or judge errors.

error_count: usize

Number of cases that failed (LLM error, parse error, or budget exceeded).

per_case: Vec<CaseScore>

Per-case scores for successfully evaluated cases, sorted by case_index.

Trait Implementations

impl Clone for EvalReport

fn clone(&self) -> EvalReport

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for EvalReport

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for EvalReport

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for EvalReport

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.