clembench v4.0 — multilingual

Nine LLMs evaluated as agents in self-play across 14 dialogue games and 30 languages: the 24 official EU languages plus Arabic, Chinese, Russian, Serbian, Turkish and Ukrainian.

v4.0 · current 30 languages 14 games 9 models ~108,000 episodes Previous benchmarks →

clemscore combines the ability to follow game instructions at all (% Played) with how well the game was played when the instructions were followed (Quality). A model has to do both to score well.

Languages

Models