Skip to content

Rulvar API reference


Rulvar API reference / @rulvar/evals / BenchmarkRunRecord

Interface: BenchmarkRunRecord

Defined in: packages/evals/src/benchmark.ts:142

The full record of one benchmark run, scored or not.

Properties

PropertyTypeDescriptionDefined in
agentDispatchesnumberagent:end events on the live stream (logical dispatches).packages/evals/src/benchmark.ts:159
costUsdnumberThe target run's cost (judge runs are separate).packages/evals/src/benchmark.ts:154
error?WireError-packages/evals/src/benchmark.ts:166
invocationsnumberagent:phase:end events on the live stream (model activations).packages/evals/src/benchmark.ts:161
judgeCostUsdnumberThe judge-run share this run's grading spent.packages/evals/src/benchmark.ts:156
metricsRecord<string, number>Extractor values for this run.packages/evals/src/benchmark.ts:165
ordinalnumber1-based ordinal in execution order.packages/evals/src/benchmark.ts:144
rejectedReasonsstring[]Why the run was excluded; empty when scored.packages/evals/src/benchmark.ts:150
runIdstring-packages/evals/src/benchmark.ts:145
scoredbooleanCounted into the percentile series.packages/evals/src/benchmark.ts:148
status"ok" | "error" | "cancelled" | "exhausted" | "suspended"-packages/evals/src/benchmark.ts:146
usageUsage-packages/evals/src/benchmark.ts:157
verdictsGraderVerdict[]-packages/evals/src/benchmark.ts:162
verificationBenchmarkVerification-packages/evals/src/benchmark.ts:163
wallMsnumberrun:start to run:end, from event timestamps.packages/evals/src/benchmark.ts:152