LLM Leaderboard – AI Rankings

关于这款应用

LLM Leaderboard is a reference tool that aggregates and displays performance data for various large language models (LLMs). It allows users to compare models from providers such as OpenAI, Anthropic, Google, and Meta based on industry-standard benchmarks including MMLU, GPQA, and HumanEval. The app presents data through interactive charts, graphs, and heatmaps covering skills like logical reasoning, coding efficiency, mathematical calculation, and content generation. Users can filter results by provider, benchmark type, price range, and performance metrics. The application provides neutral, data-driven rankings without advertisements, aiming to assist developers, researchers, and AI enthusiasts in evaluating model capabilities for integration or study purposes. It includes over 100 tracked models and updates regularly with new releases and benchmark scores.