Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Global MMLU-Lite (Chichewa, Māori, Inuktitut)

Domain:

natural language processing

Record type:

dataset
Creator:
ai-
Host:
Global MMLU-Lite is a multilingual evaluation benchmark for LLMs covering 18 languages. This dataset extends it with professional human translations for three additional low-resource languages that are not in the original: Chichewa (nya), Māori (mri), and Inuktitut (iku). Released as part of the BYOL: Bring Your Own Language Into LLMs project (paper). The original Global MMLU-Lite by Cohere

Visit

huggingface.co

Languages

Chichewa

Tags

byolmmluglobal-mmluglobal-mmlu-litehuman-translatedlow-resource-languagesevaluationbenchmark

Licenses

apache-2.0

Similar

taresco/COHERE-GLOBAL-MMLU-FILTERED-MATHCLEAR-Global/XTTS-ChichewaCLEAR-Global/YourTTS-ChichewaCLEAR-Global/Chichewa-Synthetic-ASR-DatasetAfrican Languages - OpenAI MMLU2A2I-R/MMLU-Darija

taresco/COHERE-GLOBAL-MMLU-FILTERED-MATH

This is a filtered subset of the CohereLabs/Global-MMLU dataset. This dataset only included mathemat

CLEAR-Global/XTTS-Chichewa

CLEAR-Global/YourTTS-Chichewa

CLEAR-Global/Chichewa-Synthetic-ASR-Dataset

Synthetic Chichewa ASR dataset generated using a fine-tuned version of the YourTTS model. Sample ra

African Languages - OpenAI MMLU

This is a filtered subset of the openai/MMMLU dataset. This dataset only included mathematics (abstr

2A2I-R/MMLU-Darija