Browse and submit model evaluations in LLM benchmarks
Create and manage ML pipelines with ZenML Dashboard
Explore and benchmark visual document retrieval models
Submit models for evaluation and view leaderboard
Visualize model performance on function calling tasks
Teach, test, evaluate language models with MTEB Arena
Compare LLM performance across benchmarks
View and submit machine learning model evaluations
Compare and rank LLMs using benchmark scores
Browse and evaluate ML tasks in MLIP Arena
Multilingual Text Embedding Model Pruner
Track, rank and evaluate open LLMs and chatbots
Display benchmark results
The OpenLLM Turkish leaderboard v0.2 is a tool designed to evaluate and benchmark large language models (LLMs) for the Turkish language. It provides a platform for developers and researchers to submit and compare model evaluations across various tasks and metrics specific to Turkish. This leaderboard aims to promote transparency and progress in Turkish NLP by enabling fair comparisons of model performance.
What models are supported on the leaderboard?
The leaderboard supports a variety of LLMs, including popular models like T5, BERT, and specialized Turkish models.
How are models evaluated?
Models are evaluated based on standard NLP tasks such as text classification, question answering, and language translation, using precision, recall, BLEU score, and other relevant metrics.
How often is the leaderboard updated?
The leaderboard is updated regularly with new models, datasets, and features to reflect the latest advancements in Turkish NLP.