Introducing the Open Arabic LLM Leaderboard
What changed
This initiative is particularly significant given that it directly serves over 380 million Arabic speakers worldwide. In line with contributing towards this ever-growing field, we introduce AlGhafa, a new multiple-choice evaluation benchmark for Arabic LLMs. We use a collection of publicly available datasets, as well as a newly introduced HandMade dataset consisting of 8 billion tokens.
Why it matters
A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.
How it compares
Related prior coverage to compare against:
- The Open Arabic LLM Leaderboard 2
- QIMMA قِمّة ⛰: A Quality-First Arabic LLM Leaderboard
- What's going on with the Open LLM Leaderboard?
Sources
- Introducing the Open Arabic LLM Leaderboard (huggingface-blog)primary