# Language Equality has a Price: A Systematic Investigation of Multi-turn LLM Performance for EU-24+

arXiv: https://arxiv.org/abs/2608.01395 · HTML: https://mlsanity.com/paper/2608.01395/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 41 references that are in the map.
- First posted on arXiv 2 Aug 2026.

## Builds on (most cited first, 29 of 29)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models](https://mlsanity.com/paper/2012.15613/) (2020)
- [TextWorld: A Learning Environment for Text-based Games](https://mlsanity.com/paper/1806.11532/) (2018)
- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [MEGA: Multilingual Evaluation of Generative AI](https://mlsanity.com/paper/2303.12528/) (2023)
- [Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection](https://mlsanity.com/paper/2004.10643/) (2020)
- [ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning](https://mlsanity.com/paper/2304.05613/) (2023)
- [Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models](https://mlsanity.com/paper/2305.13707/) (2023)
- [INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge](https://mlsanity.com/paper/2411.19799/) (2024)
- [PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts](https://mlsanity.com/paper/2504.18428/) (2025)
- [Clembench: Using Game Play to Evaluate Chat-Optimized Language Models as Conversational Agents](https://mlsanity.com/paper/2305.13455/) (2023)
- [AfroBench: How Good are Large Language Models on African Languages?](https://mlsanity.com/paper/2311.07978/) (2023)
- [GameArena: Evaluating LLM Reasoning through Live Computer Games](https://mlsanity.com/paper/2412.06394/) (2024)
- [The Bitter Lesson Learned from 2,000+ Multilingual Benchmarks](https://mlsanity.com/paper/2504.15521/) (2025)
- [Towards Multilingual LLM Evaluation for European Languages](https://mlsanity.com/paper/2410.08928/) (2024)
- [MultiLoKo: a multilingual local knowledge benchmark for LLMs spanning 31 languages](https://mlsanity.com/paper/2504.10356/) (2025)
- [Egalitarian Language Representation in Language Models: It All Begins with Tokenizers](https://mlsanity.com/paper/2409.11501/) (2024)
- [One ruler to measure them all: Benchmarking multilingual long-context language models](https://mlsanity.com/paper/2503.01996/) (2025)
- [ProverbEval: Exploring LLM Evaluation Challenges for Low-resource Language Understanding](https://mlsanity.com/paper/2411.05049/) (2024)
- [MuBench: Assessment of Multilingual Capabilities of Large Language Models Across 61 Languages](https://mlsanity.com/paper/2506.19468/) (2025)
- [XIFBench: Evaluating Large Language Models on Multilingual Instruction Following](https://mlsanity.com/paper/2503.07539/) (2025)
- [TALES: Text Adventure Learning Environment Suite](https://mlsanity.com/paper/2504.14128/) (2025)
- [Where Are We? Evaluating LLM Performance on African Languages](https://mlsanity.com/paper/2502.19582/) (2025)
- [TUMLU: A Unified and Native Language Understanding Benchmark for Turkic Languages](https://mlsanity.com/paper/2502.11020/) (2025)
- [A Third Paradigm for LLM Evaluation: Dialogue Game-Based Evaluation using clembench](https://mlsanity.com/paper/2507.08491/) (2025)
- [Evaluating Modern Large Language Models on Low-Resource and Morphologically Rich Languages:A Cross-Lingual Benchmark Across Cantonese, Japanese, and Turkish](https://mlsanity.com/paper/2511.10664/) (2025)

## Abstract (arXiv)

We evaluate large language models (LLMs) as language agents playing goal-directed dialogue games in self-play across 30 languages: the 24 official EU languages plus six others. Unlike static or preference-based evaluation, this paradigm is multi-turn, reference-free and programmatically scored, and because the game mechanics are language-agnostic it extends to a new language by localising a fixed set of prompt and word-list files. Evaluating nine open-weight and commercial LLMs, we find that no open-weight model covers the EU-24 well: in every official language both commercial systems outscore every open-weight model, and the two weakest average below 40 points across the EU-24. The commercial systems stay ahead even in languages with four orders of magnitude less public web text, showing that linguistic parity is achievable, but not from public crawls alone. A model's home region lifts it without closing the gap: Chinese is the strongest of all 30 languages for two Chinese-developed models, yet the best Chinese score of any model belongs to a US commercial system. Coverage is also not parity of service. Pooled over models and languages, the median non-English language costs 31% more to run than English, and scores 10% lower.