Browse and submit language model benchmarks
Submit deepfake detection models for evaluation
Compare LLM performance across benchmarks
Browse and submit LLM evaluations
Text-To-Speech (TTS) Evaluation using objective metrics.
Benchmark AI models by comparison
Launch web-based model application
Export Hugging Face models to ONNX
Create and upload a Hugging Face model card
Demo of the new, massively multilingual leaderboard
Explore GenAI model efficiency on ML.ENERGY leaderboard
Measure BERT model performance using WASM and WebGPU
Browse and submit LLM evaluations
The HHEM Leaderboard is a platform designed for model benchmarking, allowing users to browse and submit language model benchmarks. It serves as a centralized hub for comparing the performance of various language models across different tasks and datasets. The leaderboard provides a transparent and standardized way to track advancements in language model capabilities.
What does HHEM stand for?
HHEM stands for Human-Human Empirical Metrics, focusing on evaluating language models based on human-like performance benchmarks.
Can I submit my own language model benchmarks?
Yes, HHEM Leaderboard allows users to submit benchmarks for their own language models, provided they follow the submission guidelines and criteria.
How often are the benchmarks updated?
The benchmarks are updated regularly as new models are submitted or as existing models are re-evaluated with updated metrics.