25
AraGen Leaderboard
📊
Generative Tasks Evaluation of Arabic LLMs
A collection for all leaderboards related to the Arabic Language.
Generative Tasks Evaluation of Arabic LLMs
Note Generative Tasks Leaderboard for Arabic. Based on 3C3H as an evaluation metric.
Track, rank and evaluate open Arabic LLMs and chatbots
Note Ranking models on different Arabic benchmarks. Using normalized log likelihood accuracy as a metric. 2nd version.
The only leaderboard you will require for your RAG needs 🏆
Note Ranking different embedding models in retrieval and re-ranking as tasks. Using different metrics
Track, rank and evaluate open Arabic LLMs and chatbots
Note Legacy Leaderboard: Ranking models on different Arabic benchmarks. Using normalized log likelihood accuracy as a metric. The 1st version of OALL.