Maternity Case Record Digitisation - Accuracy without Nulls: leaderboard
Metric: Field-level accuracy over populated fields only (from 0-1, times 100; median over forms): share of filled-in fields whose normalised extraction exactly matches the ground truth, on the 49 real redacted Maternity Case Records of the UBOMI BUHLE Pregnancy Exposure Registry (South Africa), one form image per call with the optimised extraction prompt and JSON template, temperature 0, two attempts at valid JSON; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 78 |
| 2 | GPT-5.4 | 76 |
| 3 | Gemini 2.5 Pro | 74 |
| 4 | Gemini 2.5 Flash | 73 |
| 5 | Gemini 3.1 Flash Lite | 73 |
| 6 | Claude Sonnet 4.6 | 64 |
| 7 | Claude Opus 4.6 | 57 |
| 8 | Claude Haiku 4.5 | 51 |
| 9 | GPT-5 Mini | 31 |
Interactive version: theaggregate.ai/benchmark?slug=maternity-case-record-digitisation-accuracy-without-nulls · How It Works · Data refreshed daily, snapshot 2026-10-07.