Explore and submit NER models
Generate a data profile report
Generate financial charts from stock data
Create detailed data reports
Generate plots for GP and PFN posterior approximations
Display a treemap of languages and datasets
Explore token probability distributions with sliders
Explore and analyze RewardBench leaderboard data
More advanced and challenging multi-task evaluation
Browse and filter LLM benchmark results
Cluster data points using KMeans
Mapping Nieman Lab's 2025 Journalism Predictions
Compare classifier performance on datasets
Clinical NER Leaderboard is a platform designed to evaluate and compare Named Entity Recognition (NER) models specifically within the clinical domain. It serves as a centralized hub for researchers and developers to explore, submit, and benchmark their NER models. The leaderboard provides transparency into model performance, fostering innovation and advancements in clinical NLP.
What types of models can I submit?
You can submit any NER model designed for clinical text processing, including rule-based, machine learning, and deep learning models.
How are models evaluated?
Models are evaluated using standardized metrics such as precision, recall, F1-score, and throughput on curated clinical datasets.
Can I access the datasets used for benchmarking?
Yes, the datasets used for benchmarking are available for download, allowing you to train and fine-tune your models effectively.