RxScribe Bench - Correctness: leaderboard
Metric: Field-level F score (%; harmonic mean of credit-weighted precision and recall per run, averaged over the three runs and then over images; all fields; 200 handwritten Indian outpatient prescription images, three independent cold runs per image, image and JSON schema only, deterministic field-by-field scoring against human ground truth with no model judge). Source: arxiv.org. Saturation forecast: Around 2029. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol | 68.1 |
| 2 | Gemini 3.1 Pro (Preview) | 66.97 |
| 3 | Muse Spark 1.2 | 64.45 |
| 4 | Claude Opus 5 | 61.67 |
Interactive version: theaggregate.ai/benchmark?slug=rxscribe-bench-correctness · How It Works · Data refreshed daily, snapshot 2026-09-26.