Explore GenAI model efficiency on ML.ENERGY leaderboard
Display and filter leaderboard models
Measure BERT model performance using WASM and WebGPU
Submit models for evaluation and view leaderboard
Explore and manage STM32 ML models with the STM32AI Model Zoo dashboard
Display LLM benchmark leaderboard and info
Evaluate reward models for math reasoning
Display model benchmark results
Load AI models and prepare your space
Search for model performance across languages and benchmarks
Determine GPU requirements for large language models
Compare code model performance on benchmarks
Convert Hugging Face model repo to Safetensors
The ML.ENERGY Leaderboard is a platform designed to benchmark and compare the energy consumption and performance of various AI models. It provides a transparent and standardized way to evaluate the efficiency of different models, enabling users to make informed decisions about their implementations. The leaderboard focuses specifically on GenAI energy efficiency, helping developers and organizations identify models that balance performance with energy usage.
What is the ML.ENERGY Leaderboard?
The ML.ENERGY Leaderboard is a tool for benchmarking AI models based on their energy consumption and performance, helping users find efficient solutions.
How are models evaluated on the leaderboard?
Models are evaluated based on their energy consumption during inference and training, as well as their performance metrics such as accuracy and speed.
How often is the leaderboard updated?
The leaderboard is continuously updated with new models and data to reflect the latest advancements in AI research and development.