Persian Text Embedding Benchmark
Upload ML model to Hugging Face Hub
View and submit machine learning model evaluations
Pergel: A Unified Benchmark for Evaluating Turkish LLMs
Display and submit language model evaluations
Find and download models from Hugging Face
Evaluate RAG systems with visual analytics
Request model evaluation on COCO val 2017 dataset
Measure over-refusal in LLMs using OR-Bench
Run benchmarks on prediction models
Generate leaderboard comparing DNA models
Multilingual Text Embedding Model Pruner
Display leaderboard of language model evaluations
The PTEB Leaderboard is a comprehensive benchmarking platform designed for evaluating and comparing the performance of Persian text embedding models. It provides a centralized space to view detailed performance metrics, enabling users to understand the capabilities and limitations of various models. By leveraging this tool, researchers and developers can make informed decisions about which models best suit their specific use cases.
• Model Comparison: Compare multiple Persian text embedding models side-by-side based on their performance metrics. • Performance Metrics: View detailed benchmarks, including accuracy, F1-score, and embedding quality for different models. • Visualization Tools: Access interactive charts and graphs to better understand model performance trends. • Customizable Filters: Narrow down results based on specific criteria such as dataset, task type, or model architecture. • Community Sharing: Share benchmark results with colleagues or the broader research community. • Regular Updates: Stay up-to-date with the latest models and their performance metrics.
What is the PTEB Leaderboard?
The PTEB Leaderboard is a benchmarking platform for Persian text embedding models, providing detailed performance metrics for comparison.
Which models are supported by the PTEB Leaderboard?
The platform supports a wide range of Persian text embedding models, including state-of-the-art and community-submitted models.
How often is the leaderboard updated?
The leaderboard is updated regularly to reflect the latest advancements in Persian text embedding models and their performance metrics.