@inproceedings{singh-etal-2026-max,
title = "{MAX}-{EVAL}-11: A Large Scale Benchmark for Evaluating Large Language Models on Full-Spectrum {ICD}-11 Medical Coding",
author = "Singh, Ujjwal and
Deshwal, Sarthak and
Dube, Nitish and
Sharma, Arjun",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Roberts, Kirk and
Tsujii, Junichi",
booktitle = "{B}io{NLP} 2026",
month = jul,
year = "2026",
address = "San Diego, California",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.bionlp-1.23/",
pages = "282--291",
ISBN = "979-8-89176-434-7",
abstract = "The global transition to the ICD-11 taxonomy demands robust automated medical coding, yet comprehensive benchmarks to evaluate Large Language Models (LLMs) on this task remain absent. We introduce MAX-EVAL-11, the first large-scale benchmark for full-spectrum ICD-11 medical coding. MAX-EVAL-11 comprises 10,000 MIMIC-III discharge summaries with mapped, expert-validated ICD-11 annotations spanning 99.87{\textbackslash}{\%} of the diagnostic taxonomy. To better reflect clinical utility, we propose a novel hierarchical evaluation framework that assigns partial credit based on ICD-11{'}s 5-level structure, addressing the brittleness of traditional exact-match metrics. Our evaluation of state-of-the-art LLMs reveals significant performance gaps. The best-performing model (Claude 4 Sonnet) achieves a weighted score of 0.433, outperforming both general-purpose peers and specialized medical models (MedCoder). Crucially, all models exhibit near-zero exact match rates (0?4.8{\textbackslash}{\%}) and rely primarily on hierarchical credit, underscoring the extreme difficulty of precise ICD-11 code generation. Furthermore, the superiority of general-purpose LLMs over legacy ICD-10 medical models (with ICD-11 codelist) suggests that broad reasoning capabilities currently outweigh domain-specific training for complex taxonomy scaling."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-etal-2026-max">
<titleInfo>
<title>MAX-EVAL-11: A Large Scale Benchmark for Evaluating Large Language Models on Full-Spectrum ICD-11 Medical Coding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ujjwal</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarthak</namePart>
<namePart type="family">Deshwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitish</namePart>
<namePart type="family">Dube</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>BioNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-434-7</identifier>
</relatedItem>
<abstract>The global transition to the ICD-11 taxonomy demands robust automated medical coding, yet comprehensive benchmarks to evaluate Large Language Models (LLMs) on this task remain absent. We introduce MAX-EVAL-11, the first large-scale benchmark for full-spectrum ICD-11 medical coding. MAX-EVAL-11 comprises 10,000 MIMIC-III discharge summaries with mapped, expert-validated ICD-11 annotations spanning 99.87\textbackslash% of the diagnostic taxonomy. To better reflect clinical utility, we propose a novel hierarchical evaluation framework that assigns partial credit based on ICD-11’s 5-level structure, addressing the brittleness of traditional exact-match metrics. Our evaluation of state-of-the-art LLMs reveals significant performance gaps. The best-performing model (Claude 4 Sonnet) achieves a weighted score of 0.433, outperforming both general-purpose peers and specialized medical models (MedCoder). Crucially, all models exhibit near-zero exact match rates (0?4.8\textbackslash%) and rely primarily on hierarchical credit, underscoring the extreme difficulty of precise ICD-11 code generation. Furthermore, the superiority of general-purpose LLMs over legacy ICD-10 medical models (with ICD-11 codelist) suggests that broad reasoning capabilities currently outweigh domain-specific training for complex taxonomy scaling.</abstract>
<identifier type="citekey">singh-etal-2026-max</identifier>
<location>
<url>https://aclanthology.org/2026.bionlp-1.23/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>282</start>
<end>291</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MAX-EVAL-11: A Large Scale Benchmark for Evaluating Large Language Models on Full-Spectrum ICD-11 Medical Coding
%A Singh, Ujjwal
%A Deshwal, Sarthak
%A Dube, Nitish
%A Sharma, Arjun
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Roberts, Kirk
%Y Tsujii, Junichi
%S BioNLP 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California
%@ 979-8-89176-434-7
%F singh-etal-2026-max
%X The global transition to the ICD-11 taxonomy demands robust automated medical coding, yet comprehensive benchmarks to evaluate Large Language Models (LLMs) on this task remain absent. We introduce MAX-EVAL-11, the first large-scale benchmark for full-spectrum ICD-11 medical coding. MAX-EVAL-11 comprises 10,000 MIMIC-III discharge summaries with mapped, expert-validated ICD-11 annotations spanning 99.87\textbackslash% of the diagnostic taxonomy. To better reflect clinical utility, we propose a novel hierarchical evaluation framework that assigns partial credit based on ICD-11’s 5-level structure, addressing the brittleness of traditional exact-match metrics. Our evaluation of state-of-the-art LLMs reveals significant performance gaps. The best-performing model (Claude 4 Sonnet) achieves a weighted score of 0.433, outperforming both general-purpose peers and specialized medical models (MedCoder). Crucially, all models exhibit near-zero exact match rates (0?4.8\textbackslash%) and rely primarily on hierarchical credit, underscoring the extreme difficulty of precise ICD-11 code generation. Furthermore, the superiority of general-purpose LLMs over legacy ICD-10 medical models (with ICD-11 codelist) suggests that broad reasoning capabilities currently outweigh domain-specific training for complex taxonomy scaling.
%U https://aclanthology.org/2026.bionlp-1.23/
%P 282-291
Markdown (Informal)
[MAX-EVAL-11: A Large Scale Benchmark for Evaluating Large Language Models on Full-Spectrum ICD-11 Medical Coding](https://aclanthology.org/2026.bionlp-1.23/) (Singh et al., BioNLP 2026)
ACL