📚 3LM: A Benchmark for Arabic LLMs in STEM and Code

The 3LM benchmark has been introduced to evaluate the performance of Arabic language models specifically in STEM (Science, Technology, Engineering, and Mathematics) and coding tasks. It includes a diverse set of tasks and datasets tailored for Arabic LLMs, aiming to enhance their applicability in technical domains. This benchmark is significant for practitioners as it provides a standardized way to assess and compare the capabilities of Arabic LLMs, facilitating improvements in model training and deployment for STEM applications.