MMLU
Harbor: pendingMMLU — AI evaluation benchmark listed by awesome.
Auto57%Knowledge & Reasoning
- Samples
- N/A
- Released
- 2015
- Scores
- 0
ArabicMMLU
The focus of language model evaluation has transitioned towards reasoning and knowledge intensive tasks, driven by advancements in pretraining large models.
How to run
ltb · arabicmmlu
$ npm i -g lettokenburn-cli$ ltb bench pull arabicmmlu --n 50$ ltb bench run ./arabicmmlu -a claude-code -m anthropic/claude-opus-4-8$ ltb bench push
License is link-only: ltb bench pull fetches rows from the original host for local evaluation only and does not write a solution/ directory. Do not redistribute the generated tasks.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
0 sourced entriesNo sourced scores recorded yet.
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Reproduced by the community
All runsLoading community runs…
About
The focus of language model evaluation has transitioned towards reasoning and knowledge intensive tasks, driven by advancements in pretraining large models. While state-of-the-art models are partially trained on large Arabic texts, evaluating their performance in Arabic remains challenging due to the limited availability of relevant datasets. To bridge this gap, we present ArabicMMLU, the first multi-task language understanding benchmark for Arabic language, sourced from school exams across diverse educational levels in different countries spanning North Africa, the Levant, and the Gulf regions. Our data comprises 40 tasks and 14,575 multiple-choice questions in Modern Standard Arabic (MSA), and is carefully constructed by collaborating with native speakers in the region. Our comprehensive evaluations of 35 models reveal substantial room for improvement, particularly among the best open-source models. Notably, BLOOMZ, mT0, LLama2, and Falcon struggle to achieve a score of 50%, while even the top-performing Arabic centric model only achieves a score of 62.3%.
Available in EleutherAI lm-evaluation-harness as task family arabicmmlu (40 tasks).