Downloadable benchmark brief

Support Agent Policy Suite Buyer Brief

Generated from Edxperimental Labs benchmark data: model rows, task traces, task mix, leaderboard controls, and the next evidence to collect before production.

Executive readout

Buyer decision memo

Strong candidate; inspect cost and latency before production use.

Model classScoreRecoveryCostP95
Frontier reasoning model8682515512ms
Fast mid-tier model7970834790ms
Open-weight local model5847746042ms
Small routing model4935934816ms

Representative trace packets

Inspectable tasks behind the score

TaskDomainSplitDifficultyTop runScore
Refund policy boundary caseRefund decisionspublicMediumFrontier reasoning model88
Regional-language human handoffLanguage handoffholdoutHardFrontier reasoning model83
Subscription downgrade saveRefund decisionspublicMediumFrontier reasoning model87
PII redaction escalationPolicy lookupholdoutHardFrontier reasoning model85

Rubric

Resolution rate

Rubric

Policy compliance

Rubric

Tone control

Rubric

Escalation precision

Leaderboard controls

Controls attached to this run

FreshnessPublic sample refreshed monthly while private holdout stays sealed until replacement tasks exist.
Leakage policyDo not use tasks sourced from public examples, vendor demos, or training-contaminated snippets without replacement variants.
Repeat-run ruleRepeat any result within five points of a leaderboard boundary across at least three seeds.
Retirement ruleRetire a task when frontier and mid-tier models cluster near the ceiling or when source material becomes widely circulated.
Required provenancetraceId, createdAt, split, source, modelVersion, runSeed, reviewerNote, retirementStatus