Running 518 518 Scaling test-time compute π Enhance math problem solving by scaling test-time compute
Running on CPU Upgrade 12.6k 12.6k Open LLM Leaderboard π Track, rank and evaluate open LLMs and chatbots
Running 112 112 Open-LLM performances are plateauing, letβs make the leaderboard steep again π Update leaderboard for fair model evaluation