← 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 2026-09-14. The composite blends measured quality, latency p50, the track-specific cost metric and error rate. Method and corpora: how we measure.
| Rank | Provider | Composite | Field accuracy | Cost | Latency p50 | Field note |
|---|---|---|---|---|---|---|
| 1 |  Firecrawl |
8.76/10 | 0.95 | $0.0034 / useful | 2.6 s | On the precision test it hallucinated a null field. |
| 2 |  ScrapingBee |
8.01/10 | 0.89 | $0.018 / useful | 3.8 s | |
| 3 |  Scrapfly |
7.81/10 | 0.93 | $0.0048 / useful | 11.5 s | |
| 4 |  Zyte |
5.58/10 | 0.55 | $0.0036 / useful | 6.8 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. No per-call markup, no commission from any provider. Cost figures are priced by the 2026-09-14 run's own table; the price the gateway bills today is on each provider page.