Cohere Labs releases CulturalRiddles: a 51-language cross-cultural riddle benchmark on HF
Cohere_Labs · x · 2026-10-29
Cohere Labs open-sourced the CulturalRiddles dataset on Hugging Face to study how AI models understand culture through riddles. It includes a 6,190-riddle test split, 74.4k human annotations and 171k model answers across 28 models, spanning 51 languages (Tunisian, Levantine, Sudanese Arabic and more), 62 communities and 93 topics. Accompanying paper: arXiv 2610.29968; evaluation-only license.
Related event: Cohere Labs Open-Sources CulturalRiddles Dataset Across 51 Languages(2 posts)→
More from Research
- Axiom's agents are formalizing CFSG in 43M lines of code, possibly the largest open-source project ever — SucceededMind · 2026-10-29
- MIT's 'AI telepathy' KV-cache transfer beats text by 40% accuracy at 4x speed, across model vendors — LucaAmb · 2026-10-29
- Coding agents fail to reimplement models from papers, sparking doubts about how papers are written — charlieharris01 · 2026-10-29
- Information-theoretic scaling laws for diffusion models predict when memorization begins — davidad · 2026-10-29
- Amandine Flachs launches side project orbench — IgorCarron · 2026-10-29
- Critic says closed weights hide personas from users, but that doesn't prove models aren't general-purpose actors — aiamblichus · 2026-10-29