🇪🇸 Datasets in Spanish for LLM Evaluation

alvarobartt 's Collections

updated Sep 2

This collection contains some datasets for LLM evaluation in Spanish, from nlp.uoregon.edu, translated using ChatGPT (including English counterparts)

alvarobartt/arc-c-okapi-eval-es

Viewer • Updated Feb 28 • 2.59k • 55

Note ARC-Challenge translated version using ChatGPT
alvarobartt/mmlu-okapi-eval-es

Viewer • Updated Feb 29 • 15.1k • 5.83k • 1

Note MMLU translated version of all the subsets and splits (besides the `auxiliary_train` one) using ChatGPT
alvarobartt/hellaswag-okapi-eval-es

Viewer • Updated Feb 29 • 9.37k • 60 • 2

Note HellaSwag translated version of the `validation` split using ChatGPT
alvarobartt/truthfulqa-okapi-eval-es

Viewer • Updated Feb 28 • 789 • 51

Note TruthfulQA translated version of the `multiple_choice` subset using ChatGPT (doesn't contain English counterpart)