A new leaderboard for large language models (LLMs) has been released, showcasing various models and their performance metrics across different categories. Notably, a model achieved the top overall rank of 1 in the 70+B category, with an average score of 52.02 and an IFEval score of 80.63. Other models ranked highly include one in the 35B category, which secured the 7th position with an average score of 36.2, and another in the 13B category that ranked 1st with an average of 39.43. The leaderboard also highlights models in the 1.5B and 7B categories, with ranks ranging from 271 to 642. Performance benchmarks such as IFEval, BBH, and MMLU-PRO are included for each model, demonstrating their capabilities in various tasks. The leaderboard reflects the ongoing advancements in LLMs and their competitive landscape.