Preprint
Aug 2026
Language Equality has a Price: A Systematic Investigation of Multi-turn LLM Performance for EU-24+
Evaluating nine open-weight and commercial LLMs, it is found 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.
Sherzod Hakimov, Karl Osswald, Eszter Jelle Psurek et al.
· 0 citations