Winning Solutions

• Do you Know your Dataset? Early Benchmarking of Scientific Competence in Small Language Models. Anthony Kalaydjian (Safran Tech. France), Eric Saikali (EPFL, Swisscom. Switzerland)
• Early Signals of Scientific Knowledge: Separating Scientific Truth from Coherent Noise. Beatriz Nascimento, Daniel Gardin, Caio Rhoden, Giovani Valdrighi ( Universidade Estadual de Campinas. Brazil)

Best student solution

• Early-Stage LLM Evaluation: A Data-Driven Filtering Pipeline for MMLU. Mohammed Dahbani, Anas Ezzakri (IMT Atlantique. France)