MMLU Benchmark

What is MMLU?

MMLU (Massive Multitask Language Understanding) is a new benchmark designed to measure knowledge acquired during pretraining by evaluating models exclusively…

Released

2020-09-07

Evaluates

学科, Examination, 大语言模型, LLM, 知识储备, Knowledge, 开源收录, Open-Source, 支持, Supported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/MMLU

MMLU paper and code

• Paper https://arxiv.org/abs/2009.03300
• Code https://github.com/hendrycks/test

Which sources cite MMLU?

• MMLU

Related 学科, Examination, 大语言模型, LLM, 知识储备, Knowledge, 开源收录, Open-Source, 支持, Supported benchmarks

• A-OKVQA
• AbsPyramid
• Ada-LEval
• AECBench
• AFQMC
• AGIEval
• AIR-Bench
• AIRBench-2024