← All leaderboards
AI extraction
What this board tests: structured fields pulled from a page against an ai/natural-language schema. Every provider below ran the identical corpus on 2026-06-21. The composite blends measured quality, latency p50, cost per successful call and error rate. Method and corpora: how we measure.
| Rank | Provider | Composite | Field accuracy | Cost | Latency p50 | Field note |
|---|---|---|---|---|---|---|
| 1 |  Scrapfly |
8.96/10 | 1.00 | $0.002 / useful | 4.5 s | Extraction accuracy ranks first among the set. |
| 2 |  Firecrawl |
8.81/10 | 0.96 | $0.0052 / useful | 1.8 s | On the precision test it hallucinated a null field. |
| 3 |  ScrapingBee |
8.14/10 | 0.89 | $0.0067 / useful | 3.8 s | |
| 4 |  Zyte |
5.7/10 | 0.55 | $0.0018 / useful | 6.5 s | Custom fields aren't possible under its fixed schema. |
Low scores are published alongside high ones — a ranking you can only trust if nothing gets hidden. The gateway's fee sits on top-ups, not per call, so the order above earns us nothing either way.