cs.CLNov 17, 2026

The Shared Word: Evaluating Language Models on Dutch Word Puzzles

Authors: Rik van Noord, Maurice Voors

Organizations: CLCG, University of Groningen

Abstract

Many LLM benchmarks for languages other than English are translated, multiple-choice, or difficult to score automatically. We introduce The Shared Word (TSW-NL), a Dutch benchmark built around four core principles: it is language-specific, open-vocabulary, human-curated, and deterministically scored. Each puzzle gives three clues that describe different senses or uses of the same Dutch word. The clues are individually ambiguous, requiring the solver to combine evidence across multiple clues. We construct the benchmark from Dutch Wikipedia disambiguation pages, followed by automatic filtering and extensive manual curation. The final dataset contains 222 instances, with three independent human answers per test item. The task is clearly challenging: scores in our human study range from 49.5% to 61.0% and the highest-scoring open-weight model we tested reaches only 39.3%. Many others even score below 20%. At the same time, closed-source models show great progress: GPT-4.1 (April 2025) scores 59.2%, whereas GPT-5.6 Sol with max reasoning scores 88.8%. We believe this task provides a useful addition to Dutch model evaluation, plus a clear recipe that can be applied to construct a similar benchmark for other languages.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. MultiZebraLogic: A Multilingual Logical Reasoning Benchmark

    Nov 5, 2025Sofie Helene Bruun, Dan Saattrup SmartLogical ReasoningMultilingual Language Model Evaluation

  2. ltzGLUE: Luxembourgish General Language Understanding Evaluation

    Apr 20, 2026Alistair Plum, Felicia Körner, Anne-Marie Lutgen +8LLM EvaluationText Classification