RxScribe Bench - Fabrications per Run: leaderboard
RxScribe Bench (2026) hallucination axis: fabrication events per transcription run, counting invented medicine rows or wrongly inferred active ingredients, clinical values and administrative fields that the prescription image does not support. Mean over 600 runs on 200 handwritten prescriptions; lower is better.
Metric: Fabrication events per run (lower is better; invented medicine rows or wrongly inferred active ingredients, clinical values and non-clinical fields asserted without support in the image, summed over 600 runs and divided by the run count; 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 December 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Muse Spark 1.2 | 2.28 | #97 |
| 2 | GPT-5.6 Sol | 2.95 | #29 |
| 3 | Gemini 3.1 Pro (Preview) | 3.06 | #91 |
| 4 | Claude Opus 5 | 3.69 | #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-fabrications-per-run · How It Works · Data refreshed daily, snapshot 2026-11-12.