@inproceedings{hariri-etal-2026-ranking,
title = "Ranking Reasoning {LLM}s under Test-Time Scaling",
author = "Hariri, Mohsen and
Hinczewski, Michael and
Ma, Jing and
Chaudhary, Vipin",
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.1544/",
pages = "33437--33478",
ISBN = "979-8-89176-390-6",
abstract = "Test-time scaling evaluates reasoning LLMs by sampling multiple outputs per prompt, but ranking models in this regime remains underexplored. We formalize dense benchmark ranking under test-time scaling and introduce Scorio, a library that implements statistical ranking methods such as paired-comparison models, item response theory (IRT) models, voting rules, and graph- and spectral-based methods. Across 20 reasoning models on four Olympiad-style math benchmarks (AIME{'}24, AIME{'}25, HMMT{'}25, and BrUMO{'}25; up to N = 80 trials), most full-trial rankings agree closely with the Bayesian gold standard Bayes{\_}{\ensuremath{\mathscr{U}}}@80 (mean Kendall{'}s {\ensuremath{\tau}}{\_}b = 0.93{--}0.95), and 19{--}34 methods recover exactly the same ordering. In the single-trial regime, the best methods reach {\ensuremath{\tau}}{\_}b {\ensuremath{\approx}} 0.86.Using greedy decoding as an empirical prior (Bayes{\_}R₀@N) reduces variance at N = 1 by 16{--}52{\%}, but can bias rankings when greedy and stochastic sampling disagree. These results identify reliable ranking methods for both high- and low-budget test-time scaling. We release Scorio as an open-source library at https://github.com/mohsenhariri/scorio."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hariri-etal-2026-ranking">
<titleInfo>
<title>Ranking Reasoning LLMs under Test-Time Scaling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohsen</namePart>
<namePart type="family">Hariri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Hinczewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vipin</namePart>
<namePart type="family">Chaudhary</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>Test-time scaling evaluates reasoning LLMs by sampling multiple outputs per prompt, but ranking models in this regime remains underexplored. We formalize dense benchmark ranking under test-time scaling and introduce Scorio, a library that implements statistical ranking methods such as paired-comparison models, item response theory (IRT) models, voting rules, and graph- and spectral-based methods. Across 20 reasoning models on four Olympiad-style math benchmarks (AIME’24, AIME’25, HMMT’25, and BrUMO’25; up to N = 80 trials), most full-trial rankings agree closely with the Bayesian gold standard Bayes_\ensuremath\mathscrU@80 (mean Kendall’s \ensuremathτ_b = 0.93–0.95), and 19–34 methods recover exactly the same ordering. In the single-trial regime, the best methods reach \ensuremathτ_b \ensuremath\approx 0.86.Using greedy decoding as an empirical prior (Bayes_R₀@N) reduces variance at N = 1 by 16–52%, but can bias rankings when greedy and stochastic sampling disagree. These results identify reliable ranking methods for both high- and low-budget test-time scaling. We release Scorio as an open-source library at https://github.com/mohsenhariri/scorio.</abstract>
<identifier type="citekey">hariri-etal-2026-ranking</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1544/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>33437</start>
<end>33478</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ranking Reasoning LLMs under Test-Time Scaling
%A Hariri, Mohsen
%A Hinczewski, Michael
%A Ma, Jing
%A Chaudhary, Vipin
%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 hariri-etal-2026-ranking
%X Test-time scaling evaluates reasoning LLMs by sampling multiple outputs per prompt, but ranking models in this regime remains underexplored. We formalize dense benchmark ranking under test-time scaling and introduce Scorio, a library that implements statistical ranking methods such as paired-comparison models, item response theory (IRT) models, voting rules, and graph- and spectral-based methods. Across 20 reasoning models on four Olympiad-style math benchmarks (AIME’24, AIME’25, HMMT’25, and BrUMO’25; up to N = 80 trials), most full-trial rankings agree closely with the Bayesian gold standard Bayes_\ensuremath\mathscrU@80 (mean Kendall’s \ensuremathτ_b = 0.93–0.95), and 19–34 methods recover exactly the same ordering. In the single-trial regime, the best methods reach \ensuremathτ_b \ensuremath\approx 0.86.Using greedy decoding as an empirical prior (Bayes_R₀@N) reduces variance at N = 1 by 16–52%, but can bias rankings when greedy and stochastic sampling disagree. These results identify reliable ranking methods for both high- and low-budget test-time scaling. We release Scorio as an open-source library at https://github.com/mohsenhariri/scorio.
%U https://aclanthology.org/2026.acl-long.1544/
%P 33437-33478
Markdown (Informal)
[Ranking Reasoning LLMs under Test-Time Scaling](https://aclanthology.org/2026.acl-long.1544/) (Hariri et al., ACL 2026)
ACL
- Mohsen Hariri, Michael Hinczewski, Jing Ma, and Vipin Chaudhary. 2026. Ranking Reasoning LLMs under Test-Time Scaling. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 33437–33478, San Diego, California, United States. Association for Computational Linguistics.