BenchmarkAggregator: GPQA Diamond to Chatbot Arena – Top LLMs, Easily Extensible

BenchmarkAggregator is an open-source framework for comprehensive LLM evaluation across cutting-edge benchmarks like GPQA Diamond, MMLU Pro, and Chatbot Arena. It offers unbiased comparisons of all major language models, testing both depth and breadth of capabilities. The framework is easily extensible and powered by OpenRouter for seamless model integration. Explore our leaderboard and contribute to advancing fair AI evaluation!