Scores · formula v1

Which tool works, for each task.

Every tool gets a 0–100 score per task type and region, recomputed every Monday 00:00 UTC from private benchmarks, live calls, audits and disputes. Every input is published next to the score.

100 × (0.40A + 0.25S + 0.20P + 0.10R + 0.05L) − min(20, 500D), clamped to 0–100
A
Accuracy: share of benchmark cases where a correct result was delivered
S
Pass rate: benchmark + live calls in the last 28 days, weighted by volume
P
Audit precision: share of audited passes confirmed correct; uses A until 50 audits exist
R
Reliability: 1 − provider error/timeout rate (last 28 days)
L
Speed: task-median latency ÷ this tool's latency, capped at 1
D
Upheld disputes ÷ passed results

Live providers

The first scores are published when benchmarks run on real providers. Join the waitlist to get the first report.

Test mode (mock providers)

These are the sandbox tools that test keys call. Their scores prove the scoring pipeline end to end; they are not real providers.

Scores for test-mode mock providers
Task typeToolRegionScoreInputs (A · S · P · R · L · D)SampleWeek of
enrich_companyMock Company Enrichment
Arettic Mock Provider
GLOBAL56.50.49 · 0.60 · 0.49 · 0.72 · 1.00 · 0.00102026-09-28
enrich_personMock Person Enrichment
Arettic Mock Provider
GLOBAL56.50.49 · 0.60 · 0.49 · 0.72 · 1.00 · 0.00102026-09-28
extract_urlMock Page Extractor
Arettic Mock Provider
GLOBAL56.50.49 · 0.60 · 0.49 · 0.72 · 1.00 · 0.00102026-09-28
find_emailMock Email Finder
Arettic Mock Provider
GLOBAL56.50.49 · 0.60 · 0.49 · 0.72 · 1.00 · 0.00102026-09-28
verify_emailMock Email Verifier
Arettic Mock Provider
GLOBAL62.90.60 · 0.60 · 0.60 · 0.72 · 1.00 · 0.00102026-09-28
web_searchMock Web Search
Arettic Mock Provider
GLOBAL73.60.72 · 0.72 · 0.72 · 0.72 · 1.00 · 0.00102026-09-28

Open data under CC BY 4.0 · /scores.json · /scores.md