Every OCR / Document-AI API below is scored by running the same public-domain document set through it and computing the Character Error Rate ourselves, alongside measured latency. The numbers are first-party measurements — and sponsors cannot edit them.
Method: FUNSD (public-domain US-gov scanned forms) + a Project Gutenberg / IA printed-page slice · scored with CER (jiwer / Levenshtein) vs transcribed ground truth · latency = median of 5 runs · v1-illustrative
⚠ The numbers below are ILLUSTRATIVE samples. The method is real and reproducible — replace these with measured numbers after running the benchmark with real API accounts. No real accounts, keys, or money were used.
Featured placement puts your service at the top of the index with your logo and pitch — in front of teams actively choosing a document-AI API.
Claim or feature your listing →Placement is for sale. Your measured CER is not — every featured service shows the same unedited benchmark number.