mlsanityData to 14 Oct 2026

RxScribe Bench: A Multi-Axis Benchmark for Evaluating Vision-Language Models on Indian Outpatient Prescriptions

arXiv 2609.13280 ↗First posted 8 Sep 2026cs.CVcited by 0

On the map: Multimodal LLMs / vision-language models → Medical vision-language models

Abstract (arXiv)

Prescription transcription errors are not interchangeable. A model that fabricates a drug and a model that misreads a legible dose pose very different clinical risks, yet prescription-transcription accuracy is typically reported as a single blended figure that treats the two as equivalent. We introduce RxScribe Bench, a benchmark for evaluating vision-language models on handwritten prescription digitization that decomposes performance into four axes tied to clinical severity, rather than folding everything into a single aggregated score. Given only a prescription image and an output schema, a model produces a structured record, which is then compared field by field against a human-authored ground truth of identical shape, with each field also labeled for visibility and legibility. The four axes isolate distinct failure modes, namely Correctness, Hallucination, Engagement, and Robustness. The Robustness axis withholds its hard-field results rather than reporting one when the supporting sample falls below a minimum-evidence threshold. We evaluate frontier vision-language models on real prescriptions across independent cold runs per image, and find that no single model wins across all four axes.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 7 of its 11 references that are in the map. First posted on arXiv 8 Sep 2026.

Builds on

7 of 11 references.

References · 7

  1. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,317
  2. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Modelscited by 583
  3. 2023AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluationcited by 300
  4. 2024Know Your Limits: A Survey of Abstention in Large Language Modelscited by 121
  5. 2025From Benchmarks to Skills: Low-Rank Factors for LLM Evaluationcited by 9
  6. 2024MIRAGE: Multimodal Identification and Recognition of Annotations in Indian General Prescriptionscited by 1
  7. 2024Leveraging Deep Learning with Multi-Head Attention for Accurate Extraction of Medicine from Handwritten Prescriptionscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models
  2. 2025Human-Level and Beyond: Benchmarking Large Language Models Against Clinical Pharmacists in Prescription Review
  3. 2025How Far Have Medical Vision-Language Models Come? A Comprehensive Benchmarking Study
  4. 2024MultiMedEval: A Benchmark and a Toolkit for Evaluating Medical Vision-Language Models
  5. 2026Calibrated Triage, Not Autonomy: Confidence Estimation for Medical Vision-Language Models
  6. 2026Consistent but Dangerous: Per-Sample Safety Classification Reveals False Reliability in Medical Vision-Language Models
  7. 2026Confident but Unreliable: A Behavioral Safety Audit of Vision-Language Models on Brain MRI
  8. 2026MVC-Bench: Benchmarking Calibration of Medical Vision-Language Models