Ukraine Launches First National AI Model Ranking

The Ministry of Digital Transformation, in collaboration with the Ukrainian Catholic University and the lang-uk initiative, has launched the Ukrainian LLM Leaderboard — an open platform for evaluating large language models based on their performance in the Ukrainian language. The platform is designed to analyze the effectiveness of models, identify their strengths and weaknesses, and determine their applicability to various tasks. Models are tested on real-world tasks, including text translation, information retrieval, logical problems, school curriculum tests, mathematical calculations, and executing complex instructions. The testing results are already available on the Hugging Face platform, where users can compare models and familiarize themselves with the evaluation methodology. In the future, the team plans to expand the ranking by adding assessments of image processing, ethical considerations, and the cost of using AI in the Ukrainian language. The performance of models on governmental tasks, such as administrative procedures and handling personal data, will also be evaluated. The State Archival Service of Ukraine has provided about 10 terabytes of information for training the national large language model "Syaivo," which corresponds to a text corpus of 70,000 books.

This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.