Methodology · public and versioned

A score you can defend.

Every number in a Bench report traces to this page: the rubric that produced it, the calibration that validated the raters, and the formulas that computed it. If a measurement can't be defended, it shouldn't be sold.

The rubric

Five dimensions, 0–5 each, 25 points total.

Each evaluated output is scored on 5 dimensions with written anchors. Evaluators also assign a severity (critical / high / medium / low / none), classify failures in a fixed error taxonomy, and write a gold-standard correction for every failed item.

DimensionScore 5 anchorScore 0 anchor
Jurisdictional accuracyCorrect legal framework for the target jurisdiction, including free-zone / federal splitsAnswers under another jurisdiction’s law, or transplants foreign doctrine wholesale
Legal correctnessThe rule is stated as the authority states it, with material conditions intactThe core rule is misstated in a way that would mislead a competent reader
CompletenessAll legally required elements, exceptions, and thresholds a practitioner would flagA required element is missing and its absence changes the answer
Reasoning qualitySound application of the right authorities to the facts, in the right orderRight sources, unsound application — or conclusion asserted without analysis
Hallucination riskEvery cited authority exists, is current, and supports the propositionFabricated statute, case, or guidance presented as real

Derived metrics

Deterministic by construction.

Report metrics are pure functions of the evaluation rows — no model in the loop, no discretion at report time:

Accuracy scoremean(total / 25) × 100
Hallucination rate% items tagged hallucinated-authority, or scoring ≤ 2 on the hallucination dimension
Critical-error rate% items with severity = critical
Citation reliability100 − % items tagged unreliable-citation or hallucinated-authority
Missing-law rate% items tagged omission

Error taxonomy

Six failure classes.

Hallucinated authorityFabricated statute, case, or guidance
MisstatementReal law, wrongly stated
OmissionLegally required element missing
Wrong jurisdictionAnswered under another regime's law
Bad reasoningRight sources, unsound application
Unreliable citationReal authority, wrong proposition

Calibration

Raters are measured before they measure.

Before an expert's scores count, they complete a paid assessment and a calibration round in which a sample of items is independently double-scored by two experts. We compute exact and adjacent (±1) agreement per dimension in code. Items with any dimension differing by more than one point go to a disagreement-resolution step: a third senior reviewer resolves, and the rationale is recorded with the item.

Ongoing QA follows a published sampling curve: 100% of a new expert's first tasks are reviewed, dropping to 20% after sustained quality, then to exception-based review. Admission and retention decisions are made by a human, always.

Inter-rater agreementfirst cycle pending

Exact agreement
Adjacent (±1)

Published here after the first calibration cycle completes. We do not invent this number; an accuracy score from uncalibrated raters is noise.

Versioning & integrity

Immutable versions. Held-out sets.

Benchmark versions are immutable once released; every report names the exact version measured against. The majority of each benchmark is held out and never published, and released sample items are excluded from paid measurement — a system that memorised our public pages gains nothing.

Named results are private to each client. Published research is aggregated or anonymized, and reports state the measured test set, date, and version — a Bench score is a point-in-time measurement of a defined set, not a warranty of production safety.

Position in the landscape

Where Bench differs.

AlternativeGap Bench covers
Open academic benchmarks (e.g. LegalBench)US-centric and static; public sets can be trained on; no corrections or remediation
General eval platformsMeasure fluency and generic hallucination, not jurisdiction-specific legal correctness
Frontier-lab data vendorsServe model labs at lab scale; Bench serves the vendor, the compliance team, and the firm — with EU/UK/UAE regulatory depth and managed corrections

Read a sample report, then measure your own system.

Sample reportRequest an audit