Explore and benchmark visual document retrieval models
Open Persian LLM Leaderboard
Convert Hugging Face model repo to Safetensors
Convert PaddleOCR models to ONNX format
Measure execution times of BERT models using WebGPU and WASM
Browse and submit model evaluations in LLM benchmarks
View and submit machine learning model evaluations
Display benchmark results
Retrain models for new data at edge devices
Display genomic embedding leaderboard
Explore and submit models using the LLM Leaderboard
Download a TriplaneGaussian model checkpoint
Optimize and train foundation models using IBM's FMS
Vidore Leaderboard is a specialized tool designed for exploring and benchmarking visual document retrieval models. It serves as a platform to compare and analyze the performance of various models in the domain of visual document retrieval. This leaderboard helps researchers and developers understand the strengths and weaknesses of different models, fostering innovation and improvements in the field.
• Model Comparison: Easily compare multiple visual document retrieval models side-by-side. • Performance Metrics: Access detailed metrics and benchmarks to evaluate model effectiveness. • Filtering Options: Customize your analysis with filters based on specific criteria. • Documentation: Detailed documentation to guide users through the benchmarking process. • Regular Updates: Stay current with the latest advancements in visual document retrieval models.
What is visual document retrieval?
Visual document retrieval involves systems that retrieve documents based on visual features, such as images or diagrams, rather than text-based searches.
How do I interpret the benchmark results?
Benchmark results are presented in the form of metrics that measure model performance. Higher values typically indicate better performance, depending on the specific metric used.
Where can I find more information about the models listed?
Detailed documentation and links to model repositories are provided on the Vidore Leaderboard platform for further exploration.