<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="radwan-etal-2026-sonic">
    <titleInfo>
        <title>SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ahmed</namePart>
        <namePart type="given">Y</namePart>
        <namePart type="family">Radwan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Christos</namePart>
        <namePart type="family">Emmanouilidis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hina</namePart>
        <namePart type="family">Tabassum</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Deval</namePart>
        <namePart type="family">Pandya</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shaina</namePart>
        <namePart type="family">Raza</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Multimodal Large Language Models (MLLMs) are a major focus of recent AI research. However, most prior work focuses on static image understanding, while their ability to process audio–video data remains underexplored. This gap highlights the need for a high-quality benchmark to systematically evaluate MLLM performance in a real-world setting.\par We introduce SONIC-O1, a comprehensive, fully human-verified benchmark of \approx60 hours (231 clips) spanning 13 real-world conversational domains with 4,958 annotations and perceived demographic metadata. SONIC-O1 evaluates three capabilities: open-ended summarization, multiple-choice question (MCQ) answering, and temporal localization with supporting rationales (reasoning). Across closed- and open-source models, we find that the MCQ accuracy shows the smallest gap between model families, under their recommended settings, the best closed-source model outperforms the best open-source model by 22.6% on temporal localization.\par We further observe accuracy gaps of up to 21.4% on temporal localization across demographic groups, indicating diagnostic disparities in model behaviour. SONIC-O1 provides an open evaluation suite for temporally grounded and demographically informed multimodal understanding.\par We release SONIC-O1 for reproducibility and research: Project Page: https://vectorinstitute.github.io/sonic-o1, Dataset: https://huggingface.co/datasets/vector-institute/sonic-o1 , Code Repository: https://github.com/VectorInstitute/sonic-o1.</abstract>
    <identifier type="citekey">radwan-etal-2026-sonic</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.767/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>17786</start>
            <end>17825</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding
%A Radwan, Ahmed Y.
%A Emmanouilidis, Christos
%A Tabassum, Hina
%A Pandya, Deval
%A Raza, Shaina
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F radwan-etal-2026-sonic
%X Multimodal Large Language Models (MLLMs) are a major focus of recent AI research. However, most prior work focuses on static image understanding, while their ability to process audio–video data remains underexplored. This gap highlights the need for a high-quality benchmark to systematically evaluate MLLM performance in a real-world setting.\par We introduce SONIC-O1, a comprehensive, fully human-verified benchmark of \approx60 hours (231 clips) spanning 13 real-world conversational domains with 4,958 annotations and perceived demographic metadata. SONIC-O1 evaluates three capabilities: open-ended summarization, multiple-choice question (MCQ) answering, and temporal localization with supporting rationales (reasoning). Across closed- and open-source models, we find that the MCQ accuracy shows the smallest gap between model families, under their recommended settings, the best closed-source model outperforms the best open-source model by 22.6% on temporal localization.\par We further observe accuracy gaps of up to 21.4% on temporal localization across demographic groups, indicating diagnostic disparities in model behaviour. SONIC-O1 provides an open evaluation suite for temporally grounded and demographically informed multimodal understanding.\par We release SONIC-O1 for reproducibility and research: Project Page: https://vectorinstitute.github.io/sonic-o1, Dataset: https://huggingface.co/datasets/vector-institute/sonic-o1 , Code Repository: https://github.com/VectorInstitute/sonic-o1.
%U https://aclanthology.org/2026.emnlp-main.767/
%P 17786-17825

Markdown (Informal)

[SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding](https://aclanthology.org/2026.emnlp-main.767/) (Radwan et al., EMNLP 2026)

• SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding (Radwan et al., EMNLP 2026)

ACL

• Ahmed Y. Radwan, Christos Emmanouilidis, Hina Tabassum, Deval Pandya, and Shaina Raza. 2026. SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 17786–17825, Budapest, Hungary. Association for Computational Linguistics.