Scores ›
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. Paying never changes a score. Tools not on sale yet are scored too. Every input is in /scores.json.
Live providers
Verified email
find_verified_emailVerify email
verify_emailCompany profile
enrich_companyBest company enrichment API for AI agents
No live score for this task yet.
Person profile
enrich_personBest person enrichment API for AI agents
No live score for this task yet.
Web search
web_searchRead a page
extract_urlHow the score is made
Formula v1, the same for every tool.
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
- Until a tool has 30 results, its score is its latest benchmark run at face value, and changes only when it is benchmarked again
- From 30 results, rates from fewer than 200 data points use the 95% Wilson lower bound
- A score moves at most ±10 points a week unless the tool is paused
- Default ranking is score, with price breaking ties within 2 points (at the same price, the tool that costs Arettic less)
- Whether a tool can be bought through Arettic never affects its rank
- Scores are recomputed every Monday 00:00 UTC