@inproceedings{akyurek-etal-2026-prbench,
title = "{PRB}ench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning",
author = {Aky{\"u}rek, Afra Feyza and
Gosai, Advait and
Zhang, Chen Bo Calvin and
Gupta, Vipul and
Jeong, Jaehwan and
Gunjal, Anisha and
Rabbani, Tahseen and
Mazzone, Maria and
IV, David Randolph and
Meymand, Mohammad Mahmoudi and
Chattha, Gurshaan and
Rodriguez, Paula and
Buendia, Diego A. Mares and
Singh, Pavit and
Liu, Michael and
Chawla, Subodh and
Cline, Peter and
Ogaz, Lucy and
Montoya, Ernesto Gabriel Hern{\'a}ndez and
Wang, Zihao and
Bhatter, Pavi and
Ayestaran, Marcos and
Liu, Bing and
He, Yunzhong},
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1958/",
pages = "42297--42325",
ISBN = "979-8-89176-390-6",
abstract = "Frontier model progress is often measured using academic benchmarks that provide a limited view of performance on open-ended, economically consequential tasks in high-stakes professional domains where practical returns matter most. We introduce Professional Reasoning Bench (PRBench), a realistic, open-ended, and difficult benchmark of real-world problems in Finance and Law. We open-source its 1,100 expert-authored tasks and 19,356 expert-curated criteria, making it the largest public, rubric-based benchmark for both legal and finance domains. We recruit 182 qualified professionals, holding JDs, CFAs, or 6+ years of experience, who contributed questions inspired by their actual workflows. This process yields significant diversity, with tasks spanning 114 countries and 47 US jurisdictions. Our expert-curated rubrics are validated through a rigorous quality pipeline, including independent expert validation. Subsequent evaluation of 20 leading models reveals substantial room for improvement, with top scores of only 0.39 (Finance) and 0.37 (Legal) on our Hard subsets. We further catalog associated economic impacts of the prompts and analyze performance using human-annotated rubric categories. Common failure modes include inaccurate judgments, a lack of process transparency and incomplete reasoning, highlighting critical gaps in their reliability for professional adoption."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akyurek-etal-2026-prbench">
<titleInfo>
<title>PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Afra</namePart>
<namePart type="given">Feyza</namePart>
<namePart type="family">Akyürek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Advait</namePart>
<namePart type="family">Gosai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="given">Bo</namePart>
<namePart type="given">Calvin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vipul</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaehwan</namePart>
<namePart type="family">Jeong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anisha</namePart>
<namePart type="family">Gunjal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tahseen</namePart>
<namePart type="family">Rabbani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Mazzone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Randolph</namePart>
<namePart type="family">IV</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Mahmoudi</namePart>
<namePart type="family">Meymand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gurshaan</namePart>
<namePart type="family">Chattha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paula</namePart>
<namePart type="family">Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="given">A</namePart>
<namePart type="given">Mares</namePart>
<namePart type="family">Buendia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavit</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subodh</namePart>
<namePart type="family">Chawla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Cline</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucy</namePart>
<namePart type="family">Ogaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ernesto</namePart>
<namePart type="given">Gabriel</namePart>
<namePart type="given">Hernández</namePart>
<namePart type="family">Montoya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zihao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavi</namePart>
<namePart type="family">Bhatter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Ayestaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunzhong</namePart>
<namePart type="family">He</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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</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, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Frontier model progress is often measured using academic benchmarks that provide a limited view of performance on open-ended, economically consequential tasks in high-stakes professional domains where practical returns matter most. We introduce Professional Reasoning Bench (PRBench), a realistic, open-ended, and difficult benchmark of real-world problems in Finance and Law. We open-source its 1,100 expert-authored tasks and 19,356 expert-curated criteria, making it the largest public, rubric-based benchmark for both legal and finance domains. We recruit 182 qualified professionals, holding JDs, CFAs, or 6+ years of experience, who contributed questions inspired by their actual workflows. This process yields significant diversity, with tasks spanning 114 countries and 47 US jurisdictions. Our expert-curated rubrics are validated through a rigorous quality pipeline, including independent expert validation. Subsequent evaluation of 20 leading models reveals substantial room for improvement, with top scores of only 0.39 (Finance) and 0.37 (Legal) on our Hard subsets. We further catalog associated economic impacts of the prompts and analyze performance using human-annotated rubric categories. Common failure modes include inaccurate judgments, a lack of process transparency and incomplete reasoning, highlighting critical gaps in their reliability for professional adoption.</abstract>
<identifier type="citekey">akyurek-etal-2026-prbench</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1958/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>42297</start>
<end>42325</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning
%A Akyürek, Afra Feyza
%A Gosai, Advait
%A Zhang, Chen Bo Calvin
%A Gupta, Vipul
%A Jeong, Jaehwan
%A Gunjal, Anisha
%A Rabbani, Tahseen
%A Mazzone, Maria
%A IV, David Randolph
%A Meymand, Mohammad Mahmoudi
%A Chattha, Gurshaan
%A Rodriguez, Paula
%A Buendia, Diego A. Mares
%A Singh, Pavit
%A Liu, Michael
%A Chawla, Subodh
%A Cline, Peter
%A Ogaz, Lucy
%A Montoya, Ernesto Gabriel Hernández
%A Wang, Zihao
%A Bhatter, Pavi
%A Ayestaran, Marcos
%A Liu, Bing
%A He, Yunzhong
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F akyurek-etal-2026-prbench
%X Frontier model progress is often measured using academic benchmarks that provide a limited view of performance on open-ended, economically consequential tasks in high-stakes professional domains where practical returns matter most. We introduce Professional Reasoning Bench (PRBench), a realistic, open-ended, and difficult benchmark of real-world problems in Finance and Law. We open-source its 1,100 expert-authored tasks and 19,356 expert-curated criteria, making it the largest public, rubric-based benchmark for both legal and finance domains. We recruit 182 qualified professionals, holding JDs, CFAs, or 6+ years of experience, who contributed questions inspired by their actual workflows. This process yields significant diversity, with tasks spanning 114 countries and 47 US jurisdictions. Our expert-curated rubrics are validated through a rigorous quality pipeline, including independent expert validation. Subsequent evaluation of 20 leading models reveals substantial room for improvement, with top scores of only 0.39 (Finance) and 0.37 (Legal) on our Hard subsets. We further catalog associated economic impacts of the prompts and analyze performance using human-annotated rubric categories. Common failure modes include inaccurate judgments, a lack of process transparency and incomplete reasoning, highlighting critical gaps in their reliability for professional adoption.
%U https://aclanthology.org/2026.acl-long.1958/
%P 42297-42325
Markdown (Informal)
[PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning](https://aclanthology.org/2026.acl-long.1958/) (Akyürek et al., ACL 2026)
ACL
- Afra Feyza Akyürek, Advait Gosai, Chen Bo Calvin Zhang, Vipul Gupta, Jaehwan Jeong, Anisha Gunjal, Tahseen Rabbani, Maria Mazzone, David Randolph IV, Mohammad Mahmoudi Meymand, Gurshaan Chattha, Paula Rodriguez, Diego A. Mares Buendia, Pavit Singh, Michael Liu, Subodh Chawla, Peter Cline, Lucy Ogaz, Ernesto Gabriel Hernández Montoya, Zihao Wang, Pavi Bhatter, Marcos Ayestaran, Bing Liu, and Yunzhong He. 2026. PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 42297–42325, San Diego, California, United States. Association for Computational Linguistics.