@inproceedings{alenicheva-etal-2026-mtgbench,
title = "{MTGB}ench: A Multi-Turn Game Benchmark for Diverse {LLM} Capability Assessment",
author = "Alenicheva, Alisa and
Zykov, Timur and
Saladukha, Artsiom and
Negodin, Vladislav",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1333/",
pages = "28225--28279",
ISBN = "979-8-89176-462-0",
abstract = "Existing LLM reasoning benchmarks are largely static, single-turn, English-centric, and reliant on biased LLM-as-a-judge scoring. We present MTGBench, a bilingual (English/Russian) suite of seven multi-turn puzzle games{---}Wordle, Word Chain, Situation Puzzles, 20 Questions, Wheel of Fortune, 20 Features, and Alias{---}spanning deductive, semantic, lateral, consistency, and knowledge-retrieval reasoning. Four games use algorithmic checkers; the remaining three use a constrained LLM-as-a-rule-enforcer validated against human annotators, and episodes are regenerated natively per language rather than translated. Across 16 frontier models and a human baseline comprising 476 sessions we find that (i) rankings are highly task-dependent, (ii) chain-of-thought is near-essential for letter-level games but uneven on knowledge-driven ones, and (iii) the strongest reasoning-enabled LLMs match or exceed our collected Russian human baseline across the entire suite. Game scores align most consistently with cognitive batteries probing Causal Reasoning, Pragmatics, Planning, and Common-sense Reasoning, though these associations are game-specific rather than a single executive-function signal. Code and data are available in MTGBench github."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alenicheva-etal-2026-mtgbench">
<titleInfo>
<title>MTGBench: A Multi-Turn Game Benchmark for Diverse LLM Capability Assessment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alisa</namePart>
<namePart type="family">Alenicheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timur</namePart>
<namePart type="family">Zykov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artsiom</namePart>
<namePart type="family">Saladukha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vladislav</namePart>
<namePart type="family">Negodin</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Existing LLM reasoning benchmarks are largely static, single-turn, English-centric, and reliant on biased LLM-as-a-judge scoring. We present MTGBench, a bilingual (English/Russian) suite of seven multi-turn puzzle games—Wordle, Word Chain, Situation Puzzles, 20 Questions, Wheel of Fortune, 20 Features, and Alias—spanning deductive, semantic, lateral, consistency, and knowledge-retrieval reasoning. Four games use algorithmic checkers; the remaining three use a constrained LLM-as-a-rule-enforcer validated against human annotators, and episodes are regenerated natively per language rather than translated. Across 16 frontier models and a human baseline comprising 476 sessions we find that (i) rankings are highly task-dependent, (ii) chain-of-thought is near-essential for letter-level games but uneven on knowledge-driven ones, and (iii) the strongest reasoning-enabled LLMs match or exceed our collected Russian human baseline across the entire suite. Game scores align most consistently with cognitive batteries probing Causal Reasoning, Pragmatics, Planning, and Common-sense Reasoning, though these associations are game-specific rather than a single executive-function signal. Code and data are available in MTGBench github.</abstract>
<identifier type="citekey">alenicheva-etal-2026-mtgbench</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1333/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>28225</start>
<end>28279</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MTGBench: A Multi-Turn Game Benchmark for Diverse LLM Capability Assessment
%A Alenicheva, Alisa
%A Zykov, Timur
%A Saladukha, Artsiom
%A Negodin, Vladislav
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F alenicheva-etal-2026-mtgbench
%X Existing LLM reasoning benchmarks are largely static, single-turn, English-centric, and reliant on biased LLM-as-a-judge scoring. We present MTGBench, a bilingual (English/Russian) suite of seven multi-turn puzzle games—Wordle, Word Chain, Situation Puzzles, 20 Questions, Wheel of Fortune, 20 Features, and Alias—spanning deductive, semantic, lateral, consistency, and knowledge-retrieval reasoning. Four games use algorithmic checkers; the remaining three use a constrained LLM-as-a-rule-enforcer validated against human annotators, and episodes are regenerated natively per language rather than translated. Across 16 frontier models and a human baseline comprising 476 sessions we find that (i) rankings are highly task-dependent, (ii) chain-of-thought is near-essential for letter-level games but uneven on knowledge-driven ones, and (iii) the strongest reasoning-enabled LLMs match or exceed our collected Russian human baseline across the entire suite. Game scores align most consistently with cognitive batteries probing Causal Reasoning, Pragmatics, Planning, and Common-sense Reasoning, though these associations are game-specific rather than a single executive-function signal. Code and data are available in MTGBench github.
%U https://aclanthology.org/2026.findings-emnlp.1333/
%P 28225-28279
Markdown (Informal)
[MTGBench: A Multi-Turn Game Benchmark for Diverse LLM Capability Assessment](https://aclanthology.org/2026.findings-emnlp.1333/) (Alenicheva et al., Findings 2026)
ACL