Explore GenAI model efficiency on ML.ENERGY leaderboard
Load AI models and prepare your space
Measure over-refusal in LLMs using OR-Bench
Compare code model performance on benchmarks
Create and upload a Hugging Face model card
Explain GPU usage for model training
Browse and submit evaluations for CaselawQA benchmarks
Compare audio representation models using benchmark results
Find recent high-liked Hugging Face models
Visualize model performance on function calling tasks
Compare and rank LLMs using benchmark scores
Retrain models for new data at edge devices
Pergel: A Unified Benchmark for Evaluating Turkish LLMs
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.