@inproceedings{sokol-etal-2026-benchnavigator,
title = "{B}ench{N}avigator: A Discovery Interface for Comparing {LLM} Benchmarks",
author = "Sokol, Anna and
Vejsbjerg, Inge and
Daly, Elizabeth M. and
Piorkowski, David and
Hind, Michael and
Moniz, Nuno and
Chawla, Nitesh V.",
editor = "Akhtar, Mubashara and
Batzner, Jan and
Choshen, Leshem and
Ghosh, Avijit and
Gohar, Usman and
Mickel, Jennifer and
Pant, Ichhya and
Talat, Zeerak and
Lin, Michelle",
booktitle = "Proceedings of the Workshop on Evaluating Evaluations ({E}val{E}val)",
month = jul,
year = "2026",
address = "San Diego, CA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.evaleval-1.29/",
pages = "174--200",
ISBN = "979-8-89176-429-3",
abstract = "Evaluating large language models (LLMs) requires selecting benchmarks that fit the intended use case. However, the rapid growth of benchmarks has made discovery and comparison difficult, because practitioners must assemble information across papers, repositories, and dataset cards with heterogeneous metadata, inconsistent terminology, and uneven documentation. Prior work improves individual benchmark documentation and quality assessment, but does not provide a uniform way to compare benchmarks during discovery. We survey practitioners, analyze multi-source benchmark metadata, and identify the fields needed for effective benchmark discovery. We introduce BenchNavigator, a prototype that organizes heterogeneous metadata into a coherent, provenance-preserving interface aligned with practitioner priorities. Our results show that benchmark metadata can be presented in a comparable form without imposing new reporting burdens on benchmark producers. We frame this contribution as discovery infrastructure, not as a method for scoring benchmark quality or replacing contextual evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sokol-etal-2026-benchnavigator">
<titleInfo>
<title>BenchNavigator: A Discovery Interface for Comparing LLM Benchmarks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Sokol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inge</namePart>
<namePart type="family">Vejsbjerg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Daly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Piorkowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Hind</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuno</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitesh</namePart>
<namePart type="given">V</namePart>
<namePart type="family">Chawla</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>Proceedings of the Workshop on Evaluating Evaluations (EvalEval)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mubashara</namePart>
<namePart type="family">Akhtar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Batzner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leshem</namePart>
<namePart type="family">Choshen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avijit</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Usman</namePart>
<namePart type="family">Gohar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Mickel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ichhya</namePart>
<namePart type="family">Pant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeerak</namePart>
<namePart type="family">Talat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michelle</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, CA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-429-3</identifier>
</relatedItem>
<abstract>Evaluating large language models (LLMs) requires selecting benchmarks that fit the intended use case. However, the rapid growth of benchmarks has made discovery and comparison difficult, because practitioners must assemble information across papers, repositories, and dataset cards with heterogeneous metadata, inconsistent terminology, and uneven documentation. Prior work improves individual benchmark documentation and quality assessment, but does not provide a uniform way to compare benchmarks during discovery. We survey practitioners, analyze multi-source benchmark metadata, and identify the fields needed for effective benchmark discovery. We introduce BenchNavigator, a prototype that organizes heterogeneous metadata into a coherent, provenance-preserving interface aligned with practitioner priorities. Our results show that benchmark metadata can be presented in a comparable form without imposing new reporting burdens on benchmark producers. We frame this contribution as discovery infrastructure, not as a method for scoring benchmark quality or replacing contextual evaluation.</abstract>
<identifier type="citekey">sokol-etal-2026-benchnavigator</identifier>
<location>
<url>https://aclanthology.org/2026.evaleval-1.29/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>174</start>
<end>200</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BenchNavigator: A Discovery Interface for Comparing LLM Benchmarks
%A Sokol, Anna
%A Vejsbjerg, Inge
%A Daly, Elizabeth M.
%A Piorkowski, David
%A Hind, Michael
%A Moniz, Nuno
%A Chawla, Nitesh V.
%Y Akhtar, Mubashara
%Y Batzner, Jan
%Y Choshen, Leshem
%Y Ghosh, Avijit
%Y Gohar, Usman
%Y Mickel, Jennifer
%Y Pant, Ichhya
%Y Talat, Zeerak
%Y Lin, Michelle
%S Proceedings of the Workshop on Evaluating Evaluations (EvalEval)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, CA
%@ 979-8-89176-429-3
%F sokol-etal-2026-benchnavigator
%X Evaluating large language models (LLMs) requires selecting benchmarks that fit the intended use case. However, the rapid growth of benchmarks has made discovery and comparison difficult, because practitioners must assemble information across papers, repositories, and dataset cards with heterogeneous metadata, inconsistent terminology, and uneven documentation. Prior work improves individual benchmark documentation and quality assessment, but does not provide a uniform way to compare benchmarks during discovery. We survey practitioners, analyze multi-source benchmark metadata, and identify the fields needed for effective benchmark discovery. We introduce BenchNavigator, a prototype that organizes heterogeneous metadata into a coherent, provenance-preserving interface aligned with practitioner priorities. Our results show that benchmark metadata can be presented in a comparable form without imposing new reporting burdens on benchmark producers. We frame this contribution as discovery infrastructure, not as a method for scoring benchmark quality or replacing contextual evaluation.
%U https://aclanthology.org/2026.evaleval-1.29/
%P 174-200
Markdown (Informal)
[BenchNavigator: A Discovery Interface for Comparing LLM Benchmarks](https://aclanthology.org/2026.evaleval-1.29/) (Sokol et al., EvalEval 2026)
ACL