MMLU

Dataset Card for MMLU Dataset Summary Measuring Massive Multitask Language Understanding by Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt (ICLR 2021). This is a massive multitask test consisting of multiple-choice questions from various branches of knowledge. The

Papers using MMLU (8)

Chain of Execution Supervision Promotes General Reasoning in Large Language Models2025Control LLM: Controlled Evolution for Intelligence Retention in LLM2025Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone2024 · 158 citesART: Automatic multi-step reasoning and tool-use for large language models2023 · 50 citesThe FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale2024 · 19 citesYAYI 2: Multilingual Open-Source Large Language Models2023 · 3 citesOpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch2023 · 2 citesRead-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design2024