RxScribe Bench - Correctness: leaderboard
RxScribe Bench (2026) asks vision-language models to transcribe handwritten Indian outpatient prescriptions into a structured record given only the image and a JSON schema. Correctness is a field-level F score in percent that balances precision and recall of the filled fields, averaged over three cold runs on each of 200 prescriptions and scored deterministically against human ground truth; higher is better.
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 November 2028. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 68.1 | #29 |
| 2 | Gemini 3.1 Pro (Preview) | 66.97 | #91 |
| 3 | Muse Spark 1.2 | 64.45 | #97 |
| 4 | Claude Opus 5 | 61.67 | #20 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=rxscribe-bench-correctness · How It Works · Data refreshed daily, snapshot 2026-11-12.